Arrow Research search

Author name cluster

Sheng Liu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

35 papers
2 author rows

Possible papers

35

EAAI Journal 2026 Journal Article

Dual-domain data enhancement and lightweight deep architecture for robust powder bed defect detection

  • Zihan Yang
  • Junlai Zhao
  • Yuhao Zhai
  • Qingpeng Chen
  • Fang Dong
  • Sheng Liu

Powder-bed defect detection is essential for in-situ quality monitoring and assurance in Selective Laser Melting (SLM), where early identification of recoating-induced powder-bed anomalies—such as Recoater streaking, Recoater hopping, Incomplete spreading, and Craters—can reduce scrap and mitigate defect accumulation across layers. However, practical deployment is constrained by the scarcity of real defect samples and the high cost of data acquisition and annotation, which together limit model generalization on weak-texture surfaces and under varying imaging conditions. To address these challenges, we propose SLM-You Only Look Once (YOLO)-Light (SLM-YOLO-Light), a lightweight defect detection framework that integrates dual-domain data augmentation by combining Contrast Limited Adaptive Histogram Equalization (CLAHE)-based enhancement and Denoising Diffusion Probabilistic Model (DDPM)-based defect synthesis to improve weak-texture visibility while generating realistic defect samples with consistent powder-particle statistics. Architecturally, the proposed network replaces standard convolutions with Ghost Convolution to reduce computational redundancy, incorporates a Multi-Scale Convolutional Attention mechanism to enhance contextual perception, and adopts a Dynamic Head for adaptive cross-scale fusion and improved spatial–semantic alignment. Experiments on a self-collected SLM powder-bed dataset demonstrate that SLM-YOLO-Light achieves a mean average precision (mAP@0. 5: 0. 95) of 0. 667, representing a 9. 1% improvement over the baseline, while maintaining moderate computational complexity (4. 4 million parameters and 25. 1 ms per image). These results indicate that the proposed augmentation strategy and lightweight architecture enable accurate and efficient defect localization, offering practical potential for machine-side, near-real-time powder-bed inspection in industrial SLM workflows.

Details DOI

JBHI Journal 2026 Journal Article

Rethinking Multi-center Semi-supervised Breast Cancer Ultrasound Image Segmentation: An Intermediate-domain Perspective

  • Zhaoyi Ye
  • Yimin Zhang
  • Jin Huang
  • Du Wang
  • Sheng Liu
  • Liye Mei
  • Cheng Lei

Multi-center breast ultrasound images eg mentation aims to leverage limited labeled data from a single center to enhance model discriminability across unlabeled data from other centers. However, differences in equipment parameters, disease severity, and imaging conditions collectively contribute to significant cross domain shifts in multi-center data. In a spirit of the golden mean, we argue that constructing an intermediate domain between the source and target domains can effectively improve model generalization. Therefore, we propose a Cross-domain Few-label Generalization (CFG) framework for multi-center breast ultrasound image segmentation. Specifically, we design the Intermediate Domain Generator (IDG) to generate intermediate domain samplesthatcontain features from both the source and target domains bidirectionally, enabling the model to explicitly learn univer sal semantic representations. Additionally, we apply Swin Masked Autoencoder (MAE) to mask and reconstruct ul trasound images, simulating speckle noise encountered during clinical ultrasound acquisition, thereby increasing the diversity of intermediate domain samples. Further more, we integrate the Kolmogorov-Arnold Network (KAN) with UNet to construct KAN-UNet, integrating learnable spline functions directly onto the edges, enabling effective multi-scale perception of breast cancer lesion features. Experimental results show that even with limited labeled data from the source domain (BUSI-WHU), the CFG frame work achieves a Kappa value of 77. 17%, surpassing ten state-of-the-art methods and outperforming the second best method by 0. 78% across four multi-center ultrasound datasets (BUSI-WHU, BUSI, Dataset-B, and Dataset-C) collected from different medical centers. The code is available at https://github.com/yzygit1230/CFG.

Details DOI

AAAI Conference 2026 Conference Paper

SpatialLogic-Bench: A Diagnostic Benchmark for Task-Oriented Spatiotemporal Reasoning

  • Xiaoda Yang
  • Shenzhou Gao
  • Can Wang
  • Jiahe Zhang
  • Menglan Tang
  • Jingyang Xue
  • Sheng Liu
  • Peijian Zhang

Vision-Language Models (VLMs) have made significant progress in static perception, but their ability to understand dynamic task-oriented reasoning remains unclear. Existing benchmarks mainly focus on static spatial relationships and lack systematic assessment of dynamic reasoning capabilities. To this end, we propose SpatialLogic-Bench, a novel benchmark designed to evaluate VLMs’ understanding of spatiotemporal logic and their ability to assess task progress. The benchmark assesses two critical capabilities: first, fine-grained visual discrimination to accurately perceive subtle physical changes between state frames; second, the logical capacity to connect these changes to task goals and judge whether they indicate progress. To mitigate temporal dependency biases, we introduce a dual-task paradigm, presenting image pairs in both chronological and reversed orders while keeping task descriptions consistent. We construct a multi-scale evaluation system by varying time intervals between frames: smaller intervals test the model's fine-grained perception, while larger intervals demand more sophisticated logical inference. Empirical evaluation reveals that most VLMs experience significant performance degradation on tasks presented in inverse chronological order, indicating an over-reliance on temporal cues rather than robust reasoning abilities. SpatialLogic-Bench clearly exposes critical limitations in current models and provides valuable guidance for improving dynamic spatial perception capabilities.

PDF Details DOI

AAAI Conference 2026 Conference Paper

SRAM: Shape-Realism Alignment Metric for No Reference 3D Shape Evaluation

  • Sheng Liu
  • Tianyu Luan
  • Phani Nuney
  • Xuelu Feng
  • Junsong Yuan

3D generation and reconstruction techniques have been widely used in computer games, film, and other content creation areas. As the application grows, there is a growing demand for 3D shapes that look truly realistic. Traditional evaluation methods rely on a ground truth to measure mesh fidelity. However, in many practical cases, a shape's realism does not depend on having a ground truth reference. In this work, we propose a Shape-Realism Alignment Metric that leverages a large language model (LLM) as a bridge between mesh shape information and realism evaluation. To achieve this, we adopt a mesh encoding approach that converts 3D shapes into the language token space. A dedicated realism decoder is designed to align the language model’s output with human perception of realism. Additionally, we introduce a new dataset, RealismGrading, which provides human-annotated realism scores without the need for ground truth shapes. Our dataset includes shapes generated by 16 different algorithms on over a dozen objects, making it more representative of practical 3D shape distributions. We validate our metric's performance and generalizability through k-fold cross-validation across different objects. Experimental results show that our metric correlates well with human perceptions and outperforms existing methods, and has good generalizability.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Textured Geometry Evaluation: Perceptual 3D Textured Shape Metric via 3D Latent-Geometry Network

  • Tianyu Luan
  • Xuelu Feng
  • Zixin Zhu
  • Phani Nuney
  • Sheng Liu
  • Xuan Gong
  • David Doermann
  • Chunming Qiao

Textured high-fidelity 3D models are crucial for games, AR/VR, and film, but human-aligned evaluation methods still fall behind despite recent advances in 3D reconstruction and generation. Existing metrics, such as Chamfer Distance, often fail to align with how humans evaluate the fidelity of 3D shapes. Recent learning-based metrics attempt to improve this by relying on rendered images and 2D image quality metrics. However, these approaches face limitations due to incomplete structural coverage and sensitivity to viewpoint choices. Moreover, most methods are trained on synthetic distortions, which differ significantly from real-world distortions, resulting in a domain gap. To address these challenges, we propose a new fidelity evaluation method that is based directly on 3D meshes with texture, without relying on rendering. Our method, named Textured Geometry Evaluation TGE, jointly uses the geometry and color information to calculate the fidelity of the input textured mesh with comparison to a reference colored shape. To train and evaluate our metric, we design a human-annotated dataset with real-world distortions. Experiments show that TGE outperforms rendering-based and geometry-only methods on real-world distortion dataset.

PDF Details DOI

JBHI Journal 2025 Journal Article

EMGANet: Edge-Aware Multi-Scale Group-Mix Attention Network for Breast Cancer Ultrasound Image Segmentation

  • Jin Huang
  • Yazhao Mao
  • Jingwen Deng
  • Zhaoyi Ye
  • Yimin Zhang
  • Jingwen Zhang
  • Lan Dong
  • Hui Shen

Breast cancer is one of the most prevalent diseases for women worldwide. Early and accurate ultrasound image segmentation plays a crucial role in reducing mortality. Although deep learning methods have demonstrated remarkable segmentation potential, they still struggle with challenges in ultrasound images, including blurred boundaries and speckle noise. To generate accurate ultrasound image segmentation, this paper proposes the Edge-Aware Multi-Scale Group-Mix Attention Network (EMGANet), which generates accurate segmentation by integrating deep and edge features. The Multi-Scale Group Mix Attention block effectively aggregates both sparse global and local features, ensuring the extraction of valuable information. The subsequent Edge Feature Enhancement block then focuses on cancer boundaries, enhancing the segmentation accuracy. Therefore, EMGANet effectively tackles unclear boundaries and noise in ultrasound images. We conduct experiments on two public datasets (Dataset-B, BUSI) and one private dataset which contains 927 samples from Renmin Hospital of Wuhan University (BUSI-WHU). EMGANet demonstrates superior segmentation performance, achieving an overall accuracy (OA) of 98. 56%, a mean IoU (mIoU) of 90. 32%, and an ASSD of 6. 1 pixels on the BUSI-WHU dataset. Additionally, EMGANet performs well on two public datasets, with a mIoU of 88. 2% and an ASSD of 9. 2 pixels on Dataset-B, and a mIoU of 81. 37% and an ASSD of 18. 27 pixels on the BUSI dataset. EMGANet achieves a state-of-the-art segmentation performance of about 2% in mIoU across three datasets. In summary, the proposed EMGANet significantly improves breast cancer segmentation through Edge-Aware and Group-Mix Attention mechanisms, showing great potential for clinical applications.

Details DOI

TMLR Journal 2025 Journal Article

Making Self-supervised Learning Robust to Spurious Correlation via Learning-speed Aware Sampling

  • Weicheng Zhu
  • Sheng Liu
  • Carlos Fernandez-Granda
  • Narges Razavian

Self-supervised learning (SSL) has emerged as a powerful technique for learning rich representations from unlabeled data. The data representations can capture many underlying attributes of data, and are useful in downstream prediction tasks. In real-world settings, spurious correlations between some attributes (e.g. race, gender and age) and labels for downstream tasks often exist, e.g. disease findings are usually more prevalent among elderly patients. In this paper, we investigate SSL in the presence of spurious correlations and show that the SSL training loss can be minimized by capturing only a subset of conspicuous features relevant to those sensitive attributes, despite the presence of other important predictive features for the downstream tasks. To address this issue, we investigate the learning dynamics of SSL and observe that the learning is slower for samples that conflict with such correlations (e.g. elder patients without diseases). Motivated by these findings, we propose a learning-speed aware SSL (LA-SSL) approach, in which we sample each training data with a probability that is inversely related to its learning speed. We evaluate LA-SSL on three datasets that exhibit spurious correlations between different attributes, demonstrating the enhanced robustness of pretrained representations on downstream classification tasks.

PDF Details

ICLR Conference 2025 Conference Paper

MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine

  • Yunfei Xie
  • Ce Zhou
  • Lang Gao
  • Juncheng Wu
  • Xianhang Li
  • Hongyu Zhou
  • Sheng Liu
  • Lei Xing 0001

This paper introduces MedTrinity-25M, a comprehensive, large-scale multimodal dataset for medicine, covering over 25 million images across 10 modalities with multigranular annotations for more than 65 diseases. These multigranular annotations encompass both global information, such as modality and organ detection, and local information like ROI analysis, lesion texture, and region-wise correlations. Unlike the existing multimodal datasets, which are limited by the availability of image-text pairs, we have developed the first automated pipeline that scales up multimodal data by generating multigranular visual and textual annotations in the form of image-ROI-description triplets without the need for any paired text descriptions. Specifically, data from over 30 different sources have been collected, preprocessed, and grounded using domain-specific expert models to identify ROIs related to abnormal regions. We then build a comprehensive knowledge base and prompt multimodal large language models to perform retrieval-augmented generation with the identified ROIs as guidance, resulting in multigranular textual descriptions. Compared to existing datasets, MedTrinity-25M provides the most enriched annotations, supporting a comprehensive range of multimodal tasks such as captioning and report generation, as well as vision-centric tasks like classification and segmentation. We propose LLaVA-Tri by pretraining LLaVA on MedTrinity-25M, achieving state-of-the-art performance on VQA-RAD, SLAKE, and PathVQA, surpassing representative SOTA multimodal large language models. Furthermore, MedTrinity-25M can also be utilized to support large-scale pre-training of multimodal medical AI models, contributing to the development of future foundation models in the medical domain. We will make our dataset available. The dataset is publicly available at https://yunfeixie233.github.io/MedTrinity-25M/.

Details

NeurIPS Conference 2025 Conference Paper

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models

  • Zhongxing Xu
  • Chengzhi Liu
  • Qingyue Wei
  • Juncheng Wu
  • James Zou
  • Xin Wang
  • Yuyin Zhou
  • Sheng Liu

Test-time compute has empowered multimodal large language models to generate extended reasoning chains, yielding strong performance on tasks such as multimodal math reasoning. However, we observe that this improved reasoning ability often comes with increased hallucination: as generations become longer, models tend to drift away from image-grounded content and rely more on language priors. Attention analysis reveals that longer reasoning chains reduce focus on visual inputs, contributing to hallucination. To systematically study this phenomenon, we introduce RH-AUC, a metric that quantifies how a model's perception accuracy changes with reasoning length, enabling evaluation of whether the model preserves visual grounding while reasoning. We also release RH-Bench, a diagnostic benchmark covering diverse multimodal tasks, designed to jointly assess the balance of reasoning ability and hallucination. We find that (i) larger models generally exhibit a better balance between reasoning and perception; (ii) reasoning and perception balance depends more on the types and domains of the training data than its volume. Our findings highlight the need for evaluation frameworks that account for both reasoning quality and perceptual reliability.

PDF Details

JBHI Journal 2025 Journal Article

MRRM: Advanced Biomarker Alignment in Multi-Staining Pathology Images via Multi-Scale Ring Rotation-Invariant Matching

  • Xiaoxiao Li
  • Taobo Hu
  • Zhengxiong Li
  • Mengping Long
  • Zhaoyi Ye
  • Jin Huang
  • Yaxiaer Yalikun
  • Sheng Liu

Pathology image matching is crucial for assisting pathologists in the comprehensive diagnosis of cancerous areas. However, variations in image rotation and staining caused by inherent slide imaging techniques increase the burden on pathologists, complicating the examination of cancer across different pathology slides. To address this challenge, we introduce multi-scale ring rotation-invariant matching (MRRM), which improves image matching efficiency using ring topology, assisting pathologists in robustly aligning biomarker information across various pathology images. Specifically, by employing multi-scale rings as convolution kernels, we accurately locate keypoints from the differencing of the ring pyramid, which not only enhances the likelihood of successful pathology image matching but also supports our feature descriptor in achieving advantageous performance in rotation-invariance. Experiments show that with manually annotated golden landmarks as the standard in 81 cases, exhibiting significantly superior matching accuracy (130. 93 $\, \mu \mathrm{m}$ ) and a success rate of 93. 83% compared to other methods, particularly in cases with rotated pathology images. This meets the routine diagnostic requirements of pathologists for cancer diagnosis.

Details DOI

AAAI Conference 2025 Conference Paper

OLMD: Orientation-aware Long-term Motion Decoupling for Continuous Sign Language Recognition

  • Yiheng Yu
  • Sheng Liu
  • Yuan Feng
  • Min Xu
  • Zhelun Jin
  • Xuhua Yang

The primary challenge in continuous sign language recognition (CSLR) mainly stems from the presence of multi-orientational and long-term motions. However, current research overlooks these crucial aspects, significantly impacting accuracy. To tackle these issues, we propose a novel CSLR framework: Orientation-aware Long-term Motion Decoupling (OLMD), which efficiently aggregates long-term motions and decouples multi-orientational signals into easily interpretable components. Specifically, our innovative Long-term Motion Aggregation (LMA) module filters out static redundancy while adaptively capturing abundant features of long-term motions. We further enhance orientation awareness by decoupling complex movements into horizontal and vertical components, allowing for motion purification in both orientations. Additionally, two coupling mechanisms are proposed: stage and cross-stage coupling, which together enrich multi-scale features and improve the generalization capabilities of the model. Experimentally, OLMD shows SOTA performance on three large-scale datasets: PHOENIX14, PHOENIX14-T, and CSL-Daily. Notably, we improve the word error rate (WER) on PHOENIX14 by an absolute 1.6% compared to the previous SOTA.

PDF Details DOI

AAAI Conference 2025 Conference Paper

OTLRM: Orthogonal Learning-based Low-Rank Metric for Multi-Dimensional Inverse Problems

  • Xiangming Wang
  • Haijin Zeng
  • Jiaoyang Chen
  • Sheng Liu
  • Yongyong Chen
  • Guoqing Chao

In real-world scenarios, complex data such as multispectral images and multi-frame videos inherently exhibit robust low-rank property. This property is vital for multi-dimensional inverse problems, such as tensor completion, spectral imaging reconstruction, and multispectral image denoising. Existing tensor singular value decomposition (t-SVD) definitions rely on hand-designed or pre-given transforms, which lack flexibility for defining tensor nuclear norm (TNN). The TNN-regularized optimization problem is solved by the singular value thresholding (SVT) operator, which leverages the t-SVD framework to obtain the low-rank tensor. However, it's quite complicated to introduce SVT into deep neural network due to the numerical instability problem in solving the derivatives of the eigenvectors. In this paper, we introduce a novel data-driven generative low-rank t-SVD model based on the learnable orthogonal transform, which can be naturally solved under its representation. Prompted by the linear algebra theorem of the Householder transformation, our learnable orthogonal transform is achieved by constructing an endogenously orthogonal matrix adaptable to neural networks, optimizing it as arbitrary orthogonal matrices. Additionally, we propose a low-rank solver as a generalization of SVT, which utilizes an efficient representation of generative networks to obtain low-rank structures. Extensive experiments highlight its significant restoration enhancements.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Reducing Hallucinations in Large Vision-Language Models via Latent Space Steering

  • Sheng Liu
  • Haotian Ye
  • James Y. Zou

Hallucination poses a challenge to the deployment of large vision-language models (LVLMs) in applications. Unlike in large language models (LLMs), hallucination in LVLMs often arises from misalignments between visual inputs and textual outputs. This paper investigates the underlying mechanisms of hallucination, focusing on the unique structure of LVLMs that distinguishes them from LLMs. We identify that hallucinations often arise from the sensitivity of text decoders to vision inputs, a natural phenomenon when image encoders and text decoders are pre-trained separately. Inspired by this, we introduce Visual and Textual Intervention (VTI), a novel technique designed to reduce hallucinations by steering latent space representations during inference to enhance the stability of vision features. As a task-agnostic test-time intervention, VTI can be easily applied to any problem without additional training costs. Extensive experiments demonstrate that it can effectively reduce hallucinations and outperform baseline methods across multiple metrics, highlighting the critical role of vision feature stability in LVLMs.

Details

IROS Conference 2025 Conference Paper

Two-dimensional Trajectory Tracking of a Magnetic Continuum Robot by Optimal Magnet Manipulation

  • Lijun Hao
  • Tangwen Yang
  • Jiamiao Gong
  • Sheng Liu
  • Zhe Zheng

The steerability of catheter is critical to the success of interventional procedure. In this paper, a magnetic continuum robot is presumably mounted to the distal of a catheter to pull it in the narrow, bifurcate, tortuous pathways of the blood vessels. The continuum robot is actuated by a permanent magnet. It is linear and soft, which complicates its interaction with the magnet. However, it generates the omnidirectional deflection at its tip and improves its steerability instead. In the non-uniform field generated by a permanent magnet, besides magnetic torque, magnetic force is acting on the robot as well, and both are used to derive the dynamic equations to govern the interaction between the robot and the magnet, in terms of the Euler-Bernoulli beam theory. An iterative algorithm to calculate the magnet pose is proposed to generate an optimal moving magnetic field and actuate the robot to follow the planned trajectory at its tip. A robot prototype is fabricated, and the experimental results show that this prototype can accurately track the planned trajectories in 2D space by the magnet manipulation with a robot arm.

Details

IROS Conference 2025 Conference Paper

VISO-Grasp: Vision-Language Informed Spatial Object-centric 6-DoF Active View Planning and Grasping in Clutter and Invisibility

  • Yitian Shi
  • Di Wen 0006
  • Guanqi Chen
  • Edgar Welte
  • Sheng Liu
  • Kunyu Peng
  • Rainer Stiefelhagen
  • Rania Rayyes

We propose VISO-Grasp, a novel vision-language-informed system designed to systematically address visibility constraints for grasping in severely occluded environments. By leveraging Foundation Models (FMs) for spatial reasoning and active view planning, our framework constructs and updates an instance-centric representation of spatial relationships, enhancing grasp success under challenging occlusions. Furthermore, this representation facilitates active Next-Best-View (NBV) planning and optimizes sequential grasping strategies when direct grasping is infeasible. Additionally, we introduce a multi-view uncertainty-driven grasp fusion mechanism that refines grasp confidence and directional uncertainty in real-time, ensuring robust and stable grasp execution. Extensive real-world experiments demonstrate that VISO-Grasp achieves a success rate of 87. 5% in target-oriented grasping with the fewest grasp attempts outperforming baselines. To the best of our knowledge, VISO-Grasp is the first unified framework integrating FMs into target-aware active view planning and 6-DoF grasping in environments with severe occlusions and entire invisibility constraints. Code is available at: https://github.com/YitianShi/vMF-Contact

Details

EAAI Journal 2025 Journal Article

Wind turbine blade surface defect detection model based on improved you only look once version 10 small and integrated compression

  • Hang Liu
  • Sheng Liu
  • Zhijian Liu
  • Ben Niu
  • Jing Xie
  • Chi Luo
  • Zhiyu Shi

This paper introduces a new model built on the You Only Look Once version 10 small (YOLOv10s) baseline to address challenges in wind turbine blade surface defect detection, including low accuracy due to complex backgrounds, small targets, and dense defects, as well as issues of model over-parameterization and high memory consumption. Several improvements are incorporated to enhance detection accuracy: (1) the original Spatial Pyramid Pooling Fast (SPPF) module is replaced with a lightweight Contextual Augmentation Module (CAM-DW) to improve feature fusion, (2) Efficient Multi-Scale Attention (EMA) substitutes Partial Self-Attention (PSA) for better feature extraction, and (3) the Wise-Intersection over Union version 1 (WIoU-V1) loss function optimizes detection performance for high-density defect samples. To tackle the problem of excessive parameters and memory usage, an integrated compression method is proposed, which combines isomorphic pruning to reduce parameters and memory usage with channel-wise knowledge distillation to recover accuracy lost during pruning, thus striking a balance between model complexity and performance. Experimental results show that the proposed model reduces parameters by 69. 7 % and memory usage by 68. 1 % compared to the baseline. Its mean Average Precision mAP50 (prediction confidence threshold: 0. 5) and mAP50-95 (prediction confidence thresholds: 0. 5–0. 95) improved by 3. 3 % and 3. 8 %, respectively, while detection speed increased by 46. 7 Frames Per Second (FPS). These results demonstrate that the proposed model outperforms mainstream models, significantly enhancing the accuracy and efficiency of wind turbine blade surface defect detection, and providing crucial support for intelligent wind power equipment operation and maintenance.

Details DOI

EAAI Journal 2024 Journal Article

A conditional generative model for end-to-end stress field prediction of composite bolted joints

  • Yong Zhao
  • Yuming Liu
  • Qingyuan Lin
  • Wei Pan
  • Wencai Yu
  • Yu Ren
  • Sheng Liu

Carbon Fiber Reinforced Polymer (CFRP) laminates, prized for their lightweight and high stiffness, are extensively used in aerospace and maritime applications. Bolted joints play a crucial role in connecting these laminates. However, manufacturing variations arise during the assembly process, impacting performance due to material-related factors. Predicting the assembly stress fields of Carbon Fiber Reinforced Polymer bolted joints is of great significance in design optimization, manufacturing process control, and structural health monitoring. The currently prevalent finite element analysis methods incur extremely high computational costs, failing to meet the requirements for real-time prediction of the assembly and multiparametric design of composite bolted joints. Proposing a methodological framework for rapidly predicting the assembly physical field is necessary. This paper introduces a stress prediction framework to enhance analysis and aid material parameter design. The framework is inspired by image processing and artificial intelligence drawing by analogizing the computed physical field results to the generated images. Therefore, the Bolted Tightening Generative Adversarial Network (BT-GAN), a cascaded generative model, is proposed in this paper to predict stress fields of the composite bolted joints during assembly. The model starts with data augmentation of the stress filed results from the finite element analysis in a super-resolution network, which realizes an integral interpolation mapping from coarse-grid to fine-grid results. Then, the results of the data enhancement are fed into the subsequent conditional generative adversarial network for learning. Similar to the text-guided image generation approach, the network learns to understand the physical mapping relationships between different parameters and assembly stress fields. Moreover, the network achieves higher accuracy in stress field prediction by extraction the understanding of multi-scale features through the skip connection and the attention mechanism. This method effectively learns the physical mapping relationship between multiple parameters and the stress field, applying a graph generation approach to end-to-end predictions of the field. Compared to the results of finite element analysis from the coarse-grid, the Structure Similarity Index Measure (SSIM) of the cascaded generative network proposed in this paper has been improved from 0. 584 to 0. 962 and the Peak Signal-to-Noise Ratio (PSNR) metric has been increased from 17. 3 dB to 58. 2 dB. What's more, the mean relative error on the maximum values of the stress field has reached 6. 9%. The trained model takes only 6. 1s to complete a single prediction, significantly improving the prediction efficiency compared with finite element analysis. It is compared with the other networks commonly used for physical field prediction and shows improvement in the metrics proposed in the article. By constructing such an end-to-end stress field prediction framework during assembly, efficient forecasting for the assembly of composite bolted joints can be achieved. This is advantageous for the digital twin modeling of the assembly lines and the effective control of assembly quality, providing a powerful tool for assembly design and analysis.

Details DOI

ICRA Conference 2024 Conference Paper

Design and Fabrication of a Novel Miniature Magnetic Gripper

  • Mengde Li
  • Fuqiang Zhao
  • Xiangli Li
  • Mingchang Li
  • Sheng Liu
  • Miao Li 0002

Small-scale robots hold significant promise in the field of minimally invasive surgery (MIS). In this paper, we present a miniature magnetic gripper and develop a data-driven kinematic model. The gripper comprises four fingers, wherein each finger has a maximum size not exceeding 3mm, 4mm and 5. 5mm in three dimensions. By integrating permanent magnets and elastic ropes as internal actuation elements into the fingers, the gripper is equipped with the capability to open-close under an external magnetic field, facilitating the manipulation of small objects in confined spaces. Modeling and analysis of the magnetic gripper are undertaken, wherein the relationship between the open angle and the external magnetic field is established. The average error between the experimentally observed open angles and the model-predicted values is 2. 31°. Subsequent experiments demonstrated the necessity of the magnetic gripper model for precise manipulation, verified its excellent sensitivity to magnetic fields, and demonstrated its potential for future applications in MIS.

Details

ICML Conference 2024 Conference Paper

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

  • Sheng Liu
  • Haotian Ye
  • Lei Xing 0001
  • James Y. Zou

Large language models (LLMs) demonstrate emergent in-context learning capabilities, where they adapt to new tasks based on example demonstrations. However, in-context learning has seen limited effectiveness in many settings, is difficult to quantitatively control and takes up context window space. To overcome these limitations, we propose an alternative approach that recasts in-context learning as in-context vectors (ICV). Using ICV has two steps. We first use a forward pass on demonstration examples to create the in-context vector from the latent embedding of the LLM. This vector captures essential information about the intended task. On a new query, instead of adding demonstrations to the prompt, we shift the latent states of the LLM using the ICV. The ICV approach has several benefits: 1) it enables the LLM to more effectively follow the demonstration examples; 2) it’s easy to control by adjusting the magnitude of the ICV; 3) it reduces the length of the prompt by removing the in-context demonstrations; 4) ICV is computationally much more efficient than fine-tuning. We demonstrate that ICV achieves better performance compared to standard in-context learning and fine-tuning on diverse tasks including safety, style transfer, role-playing and formatting. Moreover, we show that we can flexibly teach LLM to simultaneously follow different types of instructions by simple vector arithmetics on the corresponding ICVs.

Details

EAAI Journal 2024 Journal Article

Learning automatic navigation control skills for miniature helical robots from human demonstrations

  • Mengde Li
  • Xutian Deng
  • Fuqiang Zhao
  • Mingchang Li
  • Sheng Liu
  • Miao Li

Magnetic micro-robotic technology holds immense potential for revolutionizing minimally invasive procedures, particularly in the realm of interventional medicine. The ability to effectively and precisely control micro-scale, magnetically actuated robots in real-world scenarios is important. Mastering this capability promises to elevate the precision and efficacy of medical interventions, thereby enhancing patient outcomes. Numerous methods were proposed in previous work and achieved significant progress. However, these efforts primarily focused on model-based strategies and control improvements, with little attention given to the manipulation of the surgeon. This paper presents an exploration of an imitation learning approach, leveraging extensive manual operation experiments, to replicate the task of robotic navigation in simulated vascular environments. The control strategies are directly acquired from experimental observations and encapsulated within a high-dimensional neural network, specifically a tailored variant of the Residual Network (ResNet). The robustness and effectiveness of our proposed methodology are validated through comprehensive experimentation. In automatic navigation trials, the average error spanned from 2. 29 mm to 3. 32 mm, leading to a mean trajectory deviation of approximately 2. 92 mm. The average error rate is 31% lower than that observed in traditional model-based Proportional Integral Derivative (PID) controller (approximately 3. 81 mm). In addition, the maximum error (4. 87 mm) is 83% of that of the traditional method (5. 85 mm). Our findings emphasize the viability and benefits of learning-based techniques in micro-robot control, paving the way for innovative control strategies in interventional surgeries applications.

Details DOI

ICML Conference 2024 Conference Paper

Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews

  • Weixin Liang
  • Zachary Izzo
  • Yaohui Zhang
  • Haley Lepp
  • Hancheng Cao
  • Xuandong Zhao
  • Lingjiao Chen
  • Haotian Ye

We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM). Our maximum likelihood model leverages expert-written and AI-generated reference texts to accurately and efficiently examine real-world LLM-use at the corpus level. We apply this approach to a case study of scientific peer review in AI conferences that took place after the release of ChatGPT: ICLR 2024, NeurIPS 2023, CoRL 2023 and EMNLP 2023. Our results suggest that between 6. 5% and 16. 9% of text submitted as peer reviews to these conferences could have been substantially modified by LLMs, i. e. beyond spell-checking or minor writing updates. The circumstances in which generated text occurs offer insight into user behavior: the estimated fraction of LLM-generated text is higher in reviews which report lower confidence, were submitted close to the deadline, and from reviewers who are less likely to respond to author rebuttals. We also observe corpus-level trends in generated text which may be too subtle to detect at the individual level, and discuss the implications of such trends on peer review. We call for future interdisciplinary work to examine how LLM use is changing our information and knowledge practices.

Details

JBHI Journal 2024 Journal Article

MSGM: An Advanced Deep Multi-Size Guiding Matching Network for Whole Slide Histopathology Images Addressing Staining Variation and Low Visibility Challenges

  • Xiaoxiao Li
  • Zhengxiong Li
  • Taobo Hu
  • Mengping Long
  • Xiao Ma
  • Jin Huang
  • Yiqiang Liu
  • Yaxiaer Yalikun

Matching whole slide histopathology images to provide comprehensive information on homologous tissues is beneficial for cancer diagnosis. However, the challenge arises with the Giga-pixel whole slide images (WSIs) when aiming for high-accuracy matching. Learning-based methods are difficult to generalize well with large-size WSIs, necessitating the integration of traditional matching methods to enhance accuracy as the size increases. In this paper, we propose a multi-size guiding matching method applicable high-accuracy requirements. Specifically, we design learning multiscale texture to train deep descriptors, called TDescNet, that trains 64 × 64 × 256 and 256 × 256 × 128 size convolution layer as C64 and C256 descriptors to overcome staining variation and low visibility challenges. Furthermore, we develop the 3D-ring descriptor using sparse keypoints to support the description of large-size WSIs. Finally, we employ C64, C256, and 3D-ring descriptors to progressively guide refined local matching, utilizing geometric consistency to identify correct matching results. Experiments show that when matching WSIs of size 4096 × 4096 pixels, our average matching error is 123. 48 μm and the success rate is 93. 02 $\%$ in 43 cases. Notably, our method achieves an average improvement of 65. 52 μm in matching accuracy compared to recent state-of-the-art methods, with enhancements ranging from 36. 27 μm to 131. 66 μm. Therefore, we achieve high-fidelity whole-slice image matching, and overcome staining variation and low visibility challenges, enabling assistance in comprehensive cancer diagnosis through matched WSIs.

Details DOI

EAAI Journal 2024 Journal Article

Sparse robust adaptive unsupervised subspace learning for dimensionality reduction

  • Weizhi Xiong
  • Guolin Yu
  • Jun Ma
  • Sheng Liu

This work is devoted to the investigation of dimension reduction problem. As an efficient dimension reduction method, much attention has been paid on unsupervised subspace learning since it does not rely on expensive labels. Firstly, we implant a robust estimator in the error term of objective function, this leads to that small coefficients can be automatically allocated to the abnormal points. Thus, our model is robust to noise and outliers. Posteriorly, the L 2, r -norm ( 1 ≤ r ≤ 2 ) is used as a measure of error, then, the performance of the model can be improved by selecting the appropriate adaptive parameter r. Further, a L 2, p -norm ( 0 < p ≤ 1 ) regularization term is added to the objective function, therefore the gained sparse subspace can further improve the efficiency and accuracy of the expression, as well as enhance the generalization ability of the model and reduce over-fitting. Moreover, an efficient algorithm with fast convergence speed is designed to solve the model. Finally, the experimental results on 14 datasets show that the subspace dimension obtained by our method is no more than 6. From the results of classification test, our algorithm has obvious advantages over the other similar six algorithms.

Details DOI

NeurIPS Conference 2024 Conference Paper

TFG: Unified Training-Free Guidance for Diffusion Models

  • Haotian Ye
  • Haowei Lin
  • Jiaqi Han
  • Minkai Xu
  • Sheng Liu
  • Yitao Liang
  • Jianzhu Ma
  • James Zou

Given an unconditional diffusion model and a predictor for a target property of interest (e. g. , a classifier), the goal of training-free guidance is to generate samples with desirable target properties without additional training. Existing methods, though effective in various individual applications, often lack theoretical grounding and rigorous testing on extensive benchmarks. As a result, they could even fail on simple tasks, and applying them to a new problem becomes unavoidably difficult. This paper introduces a novel algorithmic framework encompassing existing methods as special cases, unifying the study of training-free guidance into the analysis of an algorithm-agnostic design space. Via theoretical and empirical investigation, we propose an efficient and effective hyper-parameter searching strategy that can be readily applied to any downstream task. We systematically benchmark across 7 diffusion models on 16 tasks with 40 targets, and improve performance by 8. 5% on average. Our framework and benchmark offer a solid foundation for conditional generation in a training-free manner.

PDF Details DOI

TMLR Journal 2024 Journal Article

Understanding and Improving Transfer Learning of Deep Models via Neural Collapse

  • Xiao Li
  • Sheng Liu
  • Jinxin Zhou
  • Xinyu Lu
  • Carlos Fernandez-Granda
  • Zhihui Zhu
  • Qing Qu

With the ever-increasing complexity of large-scale pre-trained models coupled with a shortage of labeled data for downstream training, transfer learning has become the primary approach in many fields, including natural language processing, computer vision, and multi-modal learning. Despite recent progress, the fine-tuning process for large-scale pre-trained models in vision still mostly relies on trial and error. This work investigates the relationship between neural collapse (NC) and transfer learning for classification problems. NC is an intriguing while prevalent phenomenon that has been recently discovered in terms of the final-layer features and linear classifiers of trained neural networks. Specifically, during the terminal phase of training, NC implies that the variability of the features within each class diminishes to zero, while the means of features between classes are maximally and equally distanced. In this work, we examine the NC attributes of pre-trained models on both downstream and training data for transfer learning, and we find strong correlation between feature collapse and downstream performance. In particular, we discovered a systematic pattern that emerges when linear probing pre-trained models on downstream training data: the more feature collapse of pre-trained models on downstream data, the higher the transfer accuracy. Additionally, we also studied the relationship between NC and transfer accuracy on the training data. Moreover, these findings allow us to develop a principled, parameter-efficient fine-tuning method that employs skip-connection to induce the last-layer feature collapse on downstream data. Our proposed fine-tuning methods deliver good performances while reducing fine-tuning parameters by at least 90\% and mitigating overfitting in situations especially when the downstream data is scarce.

PDF Details

ICLR Conference 2023 Conference Paper

Avoiding spurious correlations via logit correction

  • Sheng Liu
  • Xu Zhang
  • Nitesh Sekhar
  • Yue Wu
  • Prateek Singhal
  • Carlos Fernandez-Granda

Empirical studies suggest that machine learning models trained with empirical risk minimization (ERM) often rely on attributes that may be spuriously correlated with the class labels. Such models typically lead to poor performance during inference for data lacking such correlations. In this work, we explicitly consider a situation where potential spurious correlations are present in the majority of training data. In contrast with existing approaches, which use the ERM model outputs to detect the samples without spurious correlations and either heuristically upweight or upsample those samples, we propose the logit correction (LC) loss, a simple yet effective improvement on the softmax cross-entropy loss, to correct the sample logit. We demonstrate that minimizing the LC loss is equivalent to maximizing the group-balanced accuracy, so the proposed LC could mitigate the negative impacts of spurious correlations. Our extensive experimental results further reveal that the proposed LC loss outperforms state-of-the-art solutions on multiple popular benchmarks by a large margin, an average 5.5% absolute improvement, without access to spurious attribute labels. LC is also competitive with oracle methods that make use of the attribute labels.

Details

NeurIPS Conference 2022 Conference Paper

Are All Losses Created Equal: A Neural Collapse Perspective

  • Jinxin Zhou
  • Chong You
  • Xiao Li
  • Kangning Liu
  • Sheng Liu
  • Qing Qu
  • Zhihui Zhu

While cross entropy (CE) is the most commonly used loss function to train deep neural networks for classification tasks, many alternative losses have been developed to obtain better empirical performance. Among them, which one is the best to use is still a mystery, because there seem to be multiple factors affecting the answer, such as properties of the dataset, the choice of network architecture, and so on. This paper studies the choice of loss function by examining the last-layer features of deep networks, drawing inspiration from a recent line work showing that the global optimal solution of CE and mean-square-error (MSE) losses exhibits a Neural Collapse phenomenon. That is, for sufficiently large networks trained until convergence, (i) all features of the same class collapse to the corresponding class mean and (ii) the means associated with different classes are in a configuration where their pairwise distances are all equal and maximized. We extend such results and show through global solution and landscape analyses that a broad family of loss functions including commonly used label smoothing (LS) and focal loss (FL) exhibits Neural Collapse. Hence, all relevant losses (i. e. , CE, LS, FL, MSE) produce equivalent features on training data. In particular, based on the unconstrained feature model assumption, we provide either the global landscape analysis for LS loss or the local landscape analysis for FL loss and show that the (only! ) global minimizers are neural collapse solutions, while all other critical points are strict saddles whose Hessian exhibit negative curvature directions either in the global scope for LS loss or in the local scope for FL loss near the optimal solution. The experiments further show that Neural Collapse features obtained from all relevant losses (i. e. , CE, LS, FL, MSE) lead to largely identical performance on test data as well, provided that the network is sufficiently large and trained until convergence.

PDF Details

ICML Conference 2022 Conference Paper

Deep Probability Estimation

  • Sheng Liu
  • Aakash Kaku
  • Weicheng Zhu
  • Matan Leibovich
  • Sreyas Mohan
  • Boyang Yu 0003
  • Haoxiang Huang
  • Laure Zanna

Reliable probability estimation is of crucial importance in many real-world applications where there is inherent (aleatoric) uncertainty. Probability-estimation models are trained on observed outcomes (e. g. whether it has rained or not, or whether a patient has died or not), because the ground-truth probabilities of the events of interest are typically unknown. The problem is therefore analogous to binary classification, with the difference that the objective is to estimate probabilities rather than predicting the specific outcome. This work investigates probability estimation from high-dimensional data using deep neural networks. There exist several methods to improve the probabilities generated by these models but they mostly focus on model (epistemic) uncertainty. For problems with inherent uncertainty, it is challenging to evaluate performance without access to ground-truth probabilities. To address this, we build a synthetic dataset to study and compare different computable metrics. We evaluate existing methods on the synthetic data as well as on three real-world probability estimation tasks, all of which involve inherent uncertainty: precipitation forecasting from radar images, predicting cancer patient survival from histopathology images, and predicting car crashes from dashcam videos. We also give a theoretical analysis of a model for high-dimensional probability estimation which reproduces several of the phenomena evinced in our experiments. Finally, we propose a new method for probability estimation using neural networks, which modifies the training process to promote output probabilities that are consistent with empirical probabilities computed from the data. The method outperforms existing approaches on most metrics on the simulated as well as real-world data.

Details

AAAI Conference 2022 Conference Paper

OVIS: Open-Vocabulary Visual Instance Search via Visual-Semantic Aligned Representation Learning

  • Sheng Liu
  • Kevin Lin
  • Lijuan Wang
  • Junsong Yuan
  • Zicheng Liu

We introduce the task of open-vocabulary visual instance search (OVIS). Given an arbitrary textual search query, Openvocabulary Visual Instance Search (OVIS) aims to return a ranked list of visual instances, i. e. , image patches, that satisfies the search intent from an image database. The term “open vocabulary” means that there are neither restrictions to the visual instance to be searched nor restrictions to the word that can be used to compose the textual search query. We propose to address such a search challenge via visual-semantic aligned representation learning (ViSA). ViSA leverages massive amount of image-caption pairs as weak image-level (not instance-level) supervision to learn a rich cross-modal semantic space where the representations of visual instances (not images) and those of textual queries are aligned, thus allowing us to measure the similarities between any visual instance and an arbitrary textual query. To evaluate the performance of ViSA, we build two datasets named OVIS40 and OVIS1400 and also introduce a pipeline for error analysis. Through extensive experiments on the two datasets, we demonstrate ViSA’s ability to search for visual instances in images not available during training given a wide range of textual queries including those composed of uncommon words. Experimental results show that ViSA achieves an mAP@50 of 27. 8% on OVIS40 and achieves a recall@30 of 21. 3% on OVIS1400 dataset under the most challenging settings.

PDF Details

ICML Conference 2022 Conference Paper

Robust Training under Label Noise by Over-parameterization

  • Sheng Liu
  • Zhihui Zhu
  • Qing Qu 0001
  • Chong You

Recently, over-parameterized deep networks, with increasingly more network parameters than training samples, have dominated the performances of modern machine learning. However, when the training data is corrupted, it has been well-known that over-parameterized networks tend to overfit and do not generalize. In this work, we propose a principled approach for robust training of over-parameterized deep networks in classification tasks where a proportion of training labels are corrupted. The main idea is yet very simple: label noise is sparse and incoherent with the network learned from clean data, so we model the noise and learn to separate it from the data. Specifically, we model the label noise via another sparse over-parameterization term, and exploit implicit algorithmic regularizations to recover and separate the underlying corruptions. Remarkably, when trained using such a simple method in practice, we demonstrate state-of-the-art test accuracy against label noise on a variety of real datasets. Furthermore, our experimental results are corroborated by theory on simplified linear models, showing that exact separation between sparse noise and low-rank data can be achieved under incoherent conditions. The work opens many interesting directions for improving over-parameterized models by using sparse over-parameterization and implicit regularization. Code is available at https: //github. com/shengliu66/SOP.

Details

NeurIPS Conference 2021 Conference Paper

Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training

  • Sheng Liu
  • Xiao Li
  • Yuexiang Zhai
  • Chong You
  • Zhihui Zhu
  • Carlos Fernandez-Granda
  • Qing Qu

Normalization techniques have become a basic component in modern convolutional neural networks (ConvNets). In particular, many recent works demonstrate that promoting the orthogonality of the weights helps train deep models and improve robustness. For ConvNets, most existing methods are based on penalizing or normalizing weight matrices derived from concatenating or flattening the convolutional kernels. These methods often destroy or ignore the benign convolutional structure of the kernels; therefore, they are often expensive or impractical for deep ConvNets. In contrast, we introduce a simple and efficient ``Convolutional Normalization'' (ConvNorm) method that can fully exploit the convolutional structure in the Fourier domain and serve as a simple plug-and-play module to be conveniently incorporated into any ConvNets. Our method is inspired by recent work on preconditioning methods for convolutional sparse coding and can effectively promote each layer's channel-wise isometry. Furthermore, we show that our ConvNorm can reduce the layerwise spectral norm of the weight matrices and hence improve the Lipschitzness of the network, leading to easier training and improved robustness for deep ConvNets. Applied to classification under noise corruptions and generative adversarial network (GAN), we show that the ConvNorm improves the robustness of common ConvNets such as ResNet and the performance of GAN. We verify our findings via numerical experiments on CIFAR and ImageNet. Our implementation is available online at \url{https: //github. com/shengliu66/ConvNorm}.

PDF Details

NeurIPS Conference 2020 Conference Paper

Early-Learning Regularization Prevents Memorization of Noisy Labels

  • Sheng Liu
  • Jonathan Niles-Weed
  • Narges Razavian
  • Carlos Fernandez-Granda

We propose a novel framework to perform classification via deep learning in the presence of noisy annotations. When trained on noisy labels, deep neural networks have been observed to first fit the training data with clean labels during an "early learning" phase, before eventually memorizing the examples with false labels. We prove that early learning and memorization are fundamental phenomena in high-dimensional classification tasks, even in simple linear models, and give a theoretical explanation in this setting. Motivated by these findings, we develop a new technique for noisy classification tasks, which exploits the progress of the early learning phase. In contrast with existing approaches, which use the model output during early learning to detect the examples with clean labels, and either ignore or attempt to correct the false labels, we take a different route and instead capitalize on early learning via regularization. There are two key elements to our approach. First, we leverage semi-supervised learning techniques to produce target probabilities based on the model outputs. Second, we design a regularization term that steers the model towards these targets, implicitly preventing memorization of the false labels. The resulting framework is shown to provide robustness to noisy annotations on several standard benchmarks and real-world datasets, where it achieves results comparable to the state of the art.

PDF Details

IS Journal 2012 Journal Article

Parallel Traffic Management System Helps 16th Asian Games

  • Gang Xiong
  • Sheng Liu
  • Xisong Dong
  • Fenghua Zhu
  • Bin Hu
  • Dong Fan
  • Zi Zhang

To overcome public transportation problems during the 16th Asian Games held in Guanhzhou China, a PtMS (Parallel Transportation Management System), a novel application of Intelligent Transportation Systems, was introduced for effective and convenient traffic management. Results show that PtMS has successfully enhanced public traffic management, raising it from experience-based policy formulation plus manual implementation to scientific computing-based policy generation plus implementation with intelligent systems.

Details DOI

ICRA Conference 1994 Conference Paper

Programming Deburring Robots Based on Human Demonstration with Direct Burr Size Measurement

  • Ken-ichiro Shimokura
  • Sheng Liu

This paper discusses a new method for teaching a deburring robot based on demonstration of human skilful motion. The robot is programmed to adjust the tool feedrate in accordance with the varying burr characteristics, such as burr size and material properties. This dynamic change of tool feedrate is motivated by the effective human skill in performing a deburring task. The relationship between the tool feedrate and burr characteristics is obtained from human demonstration data and stored in a computer as an associative memory. This associative memory enables the robot to select the tool feedrate that well matches the burr characteristics. Therefore, the robot motion is always effective in removing burrs and generating smooth finish of workpiece surface without severe tool wear. In order to identify burr characteristics, a laser displacement sensor has been used for direct burr height measurement, and a deburring process model has been applied for material property differentiation. The learned associative memory is stored and represented by a neural network, which can be easily incorporated into robot programming. Experimental results show that a robot can perform a deburring task in a manner similar to its human teacher. >

Details

ICRA Conference 1991 Conference Paper

Transfer of human skills to neural net robot controllers

  • Haruhiko Asada
  • Sheng Liu

The focus of this study is to examine the teaching data for training the neural network: whether or not the sample data provide a consistent mapping from inputs to outputs, whether some significant information is missing in the measurement of human operations, and whether the network may converge to the global minimum where the network produces a correct mapping. Conditions for a given data sample to satisfy in order to generate a consistent mapping are obtained by using Lipschitz's condition, which is known as a condition for the continuity of functions. Prior to the training of neural networks, sample data are examined and validated with Lipschitz's condition, which guarantees the consistency. This validation method is applied to a skill transfer problem of deburring robots in order to demonstrate the approach. >

Details
v2026.09.13