Author name cluster

Xiaoming 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.

25 papers

1 author row

AAAI Conference 2026 Conference Paper

MGT-Prism: Enhancing Domain Generalization for Machine-Generated Text Detection via Spectral Alignment

Shengchao Liu
Xiaoming Liu
Chengzhengxu Li
Zhaohan Zhang
Guoxin Ma
Yu Lan
Shuai Xiao

Large Language Models have shown growing ability to generate fluent and coherent texts that are highly similar to the writing style of humans. Current detectors for Machine-Generated Text (MGT) perform well when they are trained and tested in the same domain but generalize poorly to unseen domains, due to domain shift between data from different sources. In this work, we propose MGT-Prism, an MGT detection method from the perspective of the frequency domain for better domain generalization. Our key insight stems from analyzing text representations in the frequency domain, where we observe consistent spectral patterns across diverse domains, while significant discrepancies in magnitude emerge between MGT and human-written texts (HWTs). The observation initiates the design of a low frequency domain filtering module for filtering out the document-level features that are sensitive to domain shift, and a dynamic spectrum alignment strategy to extract the task-specific and domain-invariant features for improving the detector's performance in domain generalization. Extensive experiments demonstrate that MGT-Prism outperforms state‑of‑the‑art baselines by an average of 0.90% in accuracy and 0.92% in F1 score on 11 test datasets across three domain‑generalization scenarios.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models

Dingqiang Ye
Chao Fan
Zhanbo Huang
Chengwen Luo
Jianqiang Li
Shiqi Yu
Xiaoming Liu

Large vision models (LVM) based gait recognition has achieved impressive performance. However, existing LVM-based approaches may overemphasize gait priors while neglecting the intrinsic value of LVM itself, particularly the rich, distinct representations across its multi-layers. To adequately unlock LVM's potential, this work investigates the impact of layer-wise representations on downstream recognition tasks. Our analysis reveals that LVM's intermediate layers offer complementary properties across tasks, integrating them yields an impressive improvement even without rich well-designed gait priors. Building on this insight, we propose a simple and universal baseline for LVM-based gait recognition, termed BiggerGait. Comprehensive evaluations on CCPG, CAISA-B*, SUSTech1K, and CCGR_MINI validate the superiority of BiggerGait across both within- and cross-domain tasks, establishing it as a simple yet practical baseline for gait representation learning. All the models and code are available at https: //github. com/ShiqiYu/OpenGait/.

PDF Details

JBHI Journal 2025 Journal Article

Spherical Harmonics-Based Deep Learning Achieves Generalized and Accurate Diffusion Tensor Imaging

Yunwei Chen
Jialong Li
Qiqi Lu
Ye Wu
Xiaoming Liu
Yuanyuan Gao
Yanqiu Feng
Zhicheng Zhang

Diffusion tensor imaging (DTI) is a prevalent magnetic resonance imaging (MRI) technique, widely used in clinical and neuroscience research. However, the reliability of DTI is affected by the low signal-to-noise ratio inherent in diffusion-weighted (DW) images. Deep learning (DL) has shown promise in improving the quality of DTI, but its limited generalization to variable acquisition schemes hinders practical applications. This study aims to develop a generalized, accurate, and efficient DL-based DTI method. By leveraging the representation of voxel-wise diffusion MRI (dMRI) signals on the sphere using spherical harmonics (SH), we propose a novel approach that utilizes SH coefficient maps as input to a network for predicting the diffusion tensor (DT) field, enabling improved generalization. Extensive experiments were conducted on simulated and in-vivo datasets, covering various DTI application scenarios. The results demonstrate that the proposed SH-DTI method achieves advanced performance in both quantitative and qualitative analyses of DTI. Moreover, it exhibits remarkable generalization capabilities across different acquisition schemes, centers, and scanners, ensuring its broad applicability in diverse settings.

Details DOI

NeurIPS Conference 2025 Conference Paper

TRIM: Scalable 3D Gaussian Diffusion Inference with Temporal and Spatial Trimming

Zeyuan Yin
Xiaoming Liu

Recent advances in 3D Gaussian diffusion models suffer from time-intensive denoising and post-denoising processing due to the massive number of Gaussian primitives, resulting in slow generation and limited scalability along sampling trajectories. To improve the efficiency of 3D diffusion models, we propose $\textbf{TRIM}$ ($\textbf{T}$rajectory $\textbf{R}$eduction and $\textbf{I}$nstance $\textbf{M}$ask denoising), a post-training approach that incorporates both temporal and spatial trimming strategies, to accelerate inference without compromising output quality while supporting the inference-time scaling for Gaussian diffusion models. Instead of scaling denoising trajectories in a costly end-to-end manner, we develop a lightweight selector model to evaluate latent Gaussian primitives derived from multiple sampled noises, enabling early trajectory reduction by selecting candidates with high-quality potential. Furthermore, we introduce instance mask denoising to prune learnable Gaussian primitives by filtering out redundant background regions, reducing inference computation at each denoising step. Extensive experiments and analysis demonstrate that TRIM significantly improves both the efficiency and quality of 3D generation.

PDF Details

NeurIPS Conference 2024 Conference Paper

Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Models

Chengzhengxu Li
Xiaoming Liu
Zhaohan Zhang
Yichen Wang
Chen Liu
Yu Lan
Chao Shen

Recent advances in prompt optimization have notably enhanced the performance of pre-trained language models (PLMs) on downstream tasks. However, the potential of optimized prompts on domain generalization has been under-explored. To explore the nature of prompt generalization on unknown domains, we conduct pilot experiments and find that (i) Prompts gaining more attention weight from PLMs’ deep layers are more generalizable and (ii) Prompts with more stable attention distributions in PLMs’ deep layers are more generalizable. Thus, we offer a fresh objective towards domain-generalizable prompts optimization named ''Concentration'', which represents the ''lookback'' attention from the current decoding token to the prompt tokens, to increase the attention strength on prompts and reduce the fluctuation of attention distribution. We adapt this new objective to popular soft prompt and hard prompt optimization methods, respectively. Extensive experiments demonstrate that our idea improves comparison prompt optimization methods by 1. 42% for soft prompt generalization and 2. 16% for hard prompt generalization in accuracy on the multi-source domain generalization setting, while maintaining satisfying in-domain performance. The promising results validate the effectiveness of our proposed prompt optimization objective and provide key insights into domain-generalizable prompts.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Dialogue for Prompting: A Policy-Gradient-Based Discrete Prompt Generation for Few-Shot Learning

Chengzhengxu Li
Xiaoming Liu
Yichen Wang
Duyi Li
Yu Lan
Chao Shen

Prompt-based pre-trained language models (PLMs) paradigm has succeeded substantially in few-shot natural language processing (NLP) tasks. However, prior discrete prompt optimization methods require expert knowledge to design the base prompt set and identify high-quality prompts, which is costly, inefficient, and subjective. Meanwhile, existing continuous prompt optimization methods improve the performance by learning the ideal prompts through the gradient information of PLMs, whose high computational cost, and low readability and generalizability are often concerning. To address the research gap, we propose a Dialogue-comprised Policy-gradient-based Discrete Prompt Optimization (DP_2O) method. We first design a multi-round dialogue alignment strategy for readability prompt set generation based on GPT-4. Furthermore, we propose an efficient prompt screening metric to identify high-quality prompts with linear complexity. Finally, we construct a reinforcement learning (RL) framework based on policy gradients to match the prompts to inputs optimally. By training a policy network with only 0.62M parameters on the tasks in the few-shot setting, DP_2O outperforms the state-of-the-art (SOTA) method by 1.52% in accuracy on average on four open-source datasets. Moreover, subsequent experiments also demonstrate that DP_2O has good universality, robustness and generalization ability.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection

Xiufeng Song
Xiao Guo
Jiache Zhang
Qirui Li
Lei Bai
Xiaoming Liu
Guangtao Zhai
Xiaohong Liu

Large numbers of synthesized videos from diffusion models pose threats to information security and authenticity, leading to an increasing demand for generated content detection. However, existing video-level detection algorithms primarily focus on detecting facial forgeries and often fail to identify diffusion-generated content with a diverse range of semantics. To advance the field of video forensics, we propose an innovative algorithm named Multi-Modal Detection(MM-Det) for detecting diffusion-generated videos. MM-Det utilizes the profound perceptual and comprehensive abilities of Large Multi-modal Models (LMMs) by generating a Multi-Modal Forgery Representation (MMFR) from LMM's multi-modal space, enhancing its ability to detect unseen forgery content. Besides, MM-Det leverages an In-and-Across Frame Attention (IAFA) mechanism for feature augmentation in the spatio-temporal domain. A dynamic fusion strategy helps refine forgery representations for the fusion. Moreover, we construct a comprehensive diffusion video dataset, called Diffusion Video Forensics (DVF), across a wide range of forgery videos. MM-Det achieves state-of-the-art performance in DVF, demonstrating the effectiveness of our algorithm. Both source code and DVF are available at https: //github. com/SparkleXFantasy/MM-Det.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network

Xiao Guo
Vishal Asnani
Sijia Liu
Xiaoming Liu

\textit{Model Parsing} defines the task of predicting hyperparameters of the generative model (GM), given a GM-generated image as the input. Since a diverse set of hyperparameters is jointly employed by the generative model, and dependencies often exist among them, it is crucial to learn these hyperparameter dependencies for improving the model parsing performance. To explore such important dependencies, we propose a novel model parsing method called Learnable Graph Pooling Network (LGPN), in which we formulate model parsing as a graph node classification problem, using graph nodes and edges to represent hyperparameters and their dependencies, respectively. Furthermore, LGPN incorporates a learnable pooling-unpooling mechanism tailored to model parsing, which adaptively learns hyperparameter dependencies of GMs used to generate the input image. Also, we introduce a Generation Trace Capturing Network (GTC) that can efficiently identify generation traces of input images, enhancing the understanding of generated images' provenances. Empirically, we achieve state-of-the-art performance in model parsing and its extended applications, showing the superiority of the proposed LGPN.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Unified Physical-Digital Face Attack Detection

Hao Fang
Ajian Liu
Haocheng Yuan
Junze Zheng
Dingheng Zeng
Yanhong Liu
Jiankang Deng
Sergio Escalera

Face Recognition (FR) systems can suffer from physical (i. e. , print photo) and digital (i. e. , DeepFake) attacks. However, previous related work rarely considers both situations at the same time. This implies the deployment of multiple models and thus more computational burden. The main reasons for this lack of an integrated model are caused by two factors: (1) The lack of a dataset including both physical and digital attacks which the same ID covers the real face and all attack types; (2) Given the large intra-class variance between these two attacks, it is difficult to learn a compact feature space to detect both attacks simultaneously. To address these issues, we collect a Unified physical-digital Attack dataset, called UniAttackData. The dataset consists of 1, 800 participations of 2 and 12 physical and digital attacks, respectively, resulting in a total of 28, 706 videos. Then, we propose a Unified Attack Detection framework based on Vision-Language Models (VLMs), namely UniAttackDetection, which includes three main modules: the Teacher-Student Prompts (TSP) module, focused on acquiring unified and specific knowledge respectively; the Unified Knowledge Mining (UKM) module, designed to capture a comprehensive feature space; and the Sample-Level Prompt Interaction (SLPI) module, aimed at grasping sample-level semantics. These three modules seamlessly form a robust unified attack detection framework. Extensive experiments on UniAttackData and three other datasets demonstrate the superiority of our approach for unified face attack detection. Dataset link: https: //sites. google. com/view/face-anti-spoofing-challenge/dataset-download/uniattackdatacvpr2024

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models

Yihua Zhang
Chongyu Fan
Yimeng Zhang
Yuguang Yao
Jinghan Jia
Jiancheng Liu
Gaoyuan Zhang
Gaowen Liu

The technological advancements in diffusion models (DMs) have demonstrated unprecedented capabilities in text-to-image generation and are widely used in diverse applications. However, they have also raised significant societal concerns, such as the generation of harmful content and copyright disputes. Machine unlearning (MU) has emerged as a promising solution, capable of removing undesired generative capabilities from DMs. However, existing MU evaluation systems present several key challenges that can result in incomplete and inaccurate assessments. To address these issues, we propose UnlearnCanvas, a comprehensive high-resolution stylized image dataset that facilitates the evaluation of the unlearning of artistic styles and associated objects. This dataset enables the establishment of a standardized, automated evaluation framework with 7 quantitative metrics assessing various aspects of the unlearning performance for DMs. Through extensive experiments, we benchmark 9 state-of-the-art MU methods for DMs, revealing novel insights into their strengths, weaknesses, and underlying mechanisms. Additionally, we explore challenging unlearning scenarios for DMs to evaluate worst-case performance against adversarial prompts, the unlearning of finer-scale concepts, and sequential unlearning. We hope that this study can pave the way for developing more effective, accurate, and robust DM unlearning methods, ensuring safer and more ethical applications of DMs in the future. The dataset, benchmark, and codes are publicly available at this link.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

ChatGPT-Powered Hierarchical Comparisons for Image Classification

Zhiyuan Ren
Yiyang Su
Xiaoming Liu

The zero-shot open-vocabulary setting poses challenges for image classification. Fortunately, utilizing a vision-language model like CLIP, pre-trained on image-textpairs, allows for classifying images by comparing embeddings. Leveraging largelanguage models (LLMs) such as ChatGPT can further enhance CLIP’s accuracyby incorporating class-specific knowledge in descriptions. However, CLIP stillexhibits a bias towards certain classes and generates similar descriptions for similarclasses, disregarding their differences. To address this problem, we present anovel image classification framework via hierarchical comparisons. By recursivelycomparing and grouping classes with LLMs, we construct a class hierarchy. Withsuch a hierarchy, we can classify an image by descending from the top to the bottomof the hierarchy, comparing image and text embeddings at each level. Throughextensive experiments and analyses, we demonstrate that our proposed approach isintuitive, effective, and explainable. Code will be released upon publication.

PDF Details

NeurIPS Conference 2023 Conference Paper

PrObeD: Proactive Object Detection Wrapper

Vishal Asnani
Abhinav Kumar
Suya You
Xiaoming Liu

Previous research in $2D$ object detection focuses on various tasks, including detecting objects in generic and camouflaged images. These works are regarded as passive works for object detection as they take the input image as is. However, convergence to global minima is not guaranteed to be optimal in neural networks; therefore, we argue that the trained weights in the object detector are not optimal. To rectify this problem, we propose a wrapper based on proactive schemes, PrObeD, which enhances the performance of these object detectors by learning a signal. PrObeD consists of an encoder-decoder architecture, where the encoder network generates an image-dependent signal termed templates to encrypt the input images, and the decoder recovers this template from the encrypted images. We propose that learning the optimum template results in an object detector with an improved detection performance. The template acts as a mask to the input images to highlight semantics useful for the object detector. Finetuning the object detector with these encrypted images enhances the detection performance for both generic and camouflaged. Our experiments on MS-COCO, CAMO, COD$10$K, and NC$4$K datasets show improvement over different detectors after applying PrObeD. Our models/codes are available at https: //github. com/vishal3477/Proactive-Object-Detection.

PDF Details

AAAI Conference 2023 Conference Paper

RADIANT: Radar-Image Association Network for 3D Object Detection

Yunfei Long
Abhinav Kumar
Daniel Morris
Xiaoming Liu
Marcos Castro
Punarjay Chakravarty

As a direct depth sensor, radar holds promise as a tool to improve monocular 3D object detection, which suffers from depth errors, due in part to the depth-scale ambiguity. On the other hand, leveraging radar depths is hampered by difficulties in precisely associating radar returns with 3D estimates from monocular methods, effectively erasing its benefits. This paper proposes a fusion network that addresses this radar-camera association challenge. We train our network to predict the 3D offsets between radar returns and object centers, enabling radar depths to enhance the accuracy of 3D monocular detection. By using parallel radar and camera backbones, our network fuses information at both the feature level and detection level, while at the same time leveraging a state-of-the-art monocular detection technique without retraining it. Experimental results show significant improvement in mean average precision and translation error on the nuScenes dataset over monocular counterparts. Our source code is available at https://github.com/longyunf/radiant.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Tame a Wild Camera: In-the-Wild Monocular Camera Calibration

Shengjie Zhu
Abhinav Kumar
Masa Hu
Xiaoming Liu

3D sensing for monocular in-the-wild images, e. g. , depth estimation and 3D object detection, has become increasingly important. However, the unknown intrinsic parameter hinders their development and deployment. Previous methods for the monocular camera calibration rely on specific 3D objects or strong geometry prior, such as using a checkerboard or imposing a Manhattan World assumption. This work instead calibrates intrinsic via exploiting the monocular 3D prior. Given an undistorted image as input, our method calibrates the complete 4 Degree-of-Freedom (DoF) intrinsic parameters. First, we show intrinsic is determined by the two well-studied monocular priors: monocular depthmap and surface normal map. However, this solution necessitates a low-bias and low-variance depth estimation. Alternatively, we introduce the incidence field, defined as the incidence rays between points in 3D space and pixels in the 2D imaging plane. We show that: 1) The incidence field is a pixel-wise parametrization of the intrinsic invariant to image cropping and resizing. 2) The incidence field is a learnable monocular 3D prior, determined pixel-wisely by up-to-sacle monocular depthmap and surface normal. With the estimated incidence field, a robust RANSAC algorithm recovers intrinsic. We show the effectiveness of our method through superior performance on synthetic and zero-shot testing datasets. Beyond calibration, we demonstrate downstream applications in image manipulation detection & restoration, uncalibrated two-view pose estimation, and 3D sensing.

PDF Details

NeurIPS Conference 2022 Conference Paper

Cluster and Aggregate: Face Recognition with Large Probe Set

Minchul Kim
Feng Liu
Anil K Jain
Xiaoming Liu

Feature fusion plays a crucial role in unconstrained face recognition where inputs (probes) comprise of a set of $N$ low quality images whose individual qualities vary. Advances in attention and recurrent modules have led to feature fusion that can model the relationship among the images in the input set. However, attention mechanisms cannot scale to large $N$ due to their quadratic complexity and recurrent modules suffer from input order sensitivity. We propose a two-stage feature fusion paradigm, Cluster and Aggregate, that can both scale to large $N$ and maintain the ability to perform sequential inference with order invariance. Specifically, Cluster stage is a linear assignment of $N$ inputs to $M$ global cluster centers, and Aggregation stage is a fusion over $M$ clustered features. The clustered features play an integral role when the inputs are sequential as they can serve as a summarization of past features. By leveraging the order-invariance of incremental averaging operation, we design an update rule that achieves batch-order invariance, which guarantees that the contributions of early image in the sequence do not diminish as time steps increase. Experiments on IJB-B and IJB-S benchmark datasets show the superiority of the proposed two-stage paradigm in unconstrained face recognition.

PDF Details

AAAI Conference 2022 Conference Paper

MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation

Safa C. Medin
Bernhard Egger
Anoop Cherian
Ye Wang
Joshua B. Tenenbaum
Xiaoming Liu
Tim K. Marks

Recent advances in generative adversarial networks (GANs) have led to remarkable achievements in face image synthesis. While methods that use style-based GANs can generate strikingly photorealistic face images, it is often difficult to control the characteristics of the generated faces in a meaningful and disentangled way. Prior approaches aim to achieve such semantic control and disentanglement within the latent space of a previously trained GAN. In contrast, we propose a framework that a priori models physical attributes of the face such as 3D shape, albedo, pose, and lighting explicitly, thus providing disentanglement by design. Our method, MOST-GAN, integrates the expressive power and photorealism of stylebased GANs with the physical disentanglement and flexibility of nonlinear 3D morphable models, which we couple with a state-of-the-art 2D hair manipulation network. MOST-GAN achieves photorealistic manipulation of portrait images with fully disentangled 3D control over their physical attributes, enabling extreme manipulation of lighting, facial expression, and pose variations up to full profile view.

PDF Details

YNIMG Journal 2021 Journal Article

MTANS: Multi-Scale Mean Teacher Combined Adversarial Network with Shape-Aware Embedding for Semi-Supervised Brain Lesion Segmentation

Gaoxiang Chen
Jintao Ru
Yilin Zhou
Islem Rekik
Zhifang Pan
Xiaoming Liu
Yezhi Lin
Beichen Lu

The annotation of brain lesion images is a key step in clinical diagnosis and treatment of a wide spectrum of brain diseases. In recent years, segmentation methods based on deep learning have gained unprecedented popularity, leveraging a large amount of data with high-quality voxel-level annotations. However, due to the limited time clinicians can provide for the cumbersome task of manual image segmentation, semi-supervised medical image segmentation methods present an alternative solution as they require only a few labeled samples for training. In this paper, we propose a novel semi-supervised segmentation framework that combines improved mean teacher and adversarial network. Specifically, our framework consists of (i) a student model and a teacher model for segmenting the target and generating the signed distance maps of object surfaces, and (ii) a discriminator network for extracting hierarchical features and distinguishing the signed distance maps of labeled and unlabeled data. Besides, based on two different adversarial learning processes, a multi-scale feature consistency loss derived from the student and teacher models is proposed, and a shape-aware embedding scheme is integrated into our framework. We evaluated the proposed method on the public brain lesion datasets from ISBI 2015, ISLES 2015, and BRATS 2018 for the multiple sclerosis lesion, ischemic stroke lesion, and brain tumor segmentation respectively. Experiments demonstrate that our method can effectively leverage unlabeled data while outperforming the supervised baseline and other state-of-the-art semi-supervised methods trained with the same labeled data. The proposed framework is suitable for joint training of limited labeled data and additional unlabeled data, which is expected to reduce the effort of obtaining annotated images.

Details DOI

NeurIPS Conference 2021 Conference Paper

Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Image

Feng Liu
Xiaoming Liu

Inferring 3D locations and shapes of multiple objects from a single 2D image is a long-standing objective of computer vision. Most of the existing works either predict one of these 3D properties or focus on solving both for a single object. One fundamental challenge lies in how to learn an effective representation of the image that is well-suited for 3D detection and reconstruction. In this work, we propose to learn a regular grid of 3D voxel features from the input image which is aligned with 3D scene space via a 3D feature lifting operator. Based on the 3D voxel features, our novel CenterNet-3D detection head formulates the 3D detection as keypoint detection in the 3D space. Moreover, we devise an efficient coarse-to-fine reconstruction module, including coarse-level voxelization and a novel local PCA-SDF shape representation, which enables fine detail reconstruction and two orders of magnitude faster inference than prior methods. With complementary supervision from both 3D detection and reconstruction, one enables the 3D voxel features to be geometry and context preserving, benefiting both tasks. The effectiveness of our approach is demonstrated through 3D detection and reconstruction on single-object and multiple-object scenarios.

PDF Details

NeurIPS Conference 2020 Conference Paper

Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence

Feng Liu
Xiaoming Liu

The goal of this paper is to learn dense 3D shape correspondence for topology-varying objects in an unsupervised manner. Conventional implicit functions estimate the occupancy of a 3D point given a shape latent code. Instead, our novel implicit function produces a part embedding vector for each 3D point, which is assumed to be similar to its densely corresponded point in another 3D shape of the same object category. Furthermore, we implement dense correspondence through an inverse function mapping from the part embedding to a corresponded 3D point. Both functions are jointly learned with several effective loss functions to realize our assumption, together with the encoder generating the shape latent code. During inference, if a user selects an arbitrary point on the source shape, our algorithm can automatically generate a confidence score indicating whether there is a correspondence on the target shape, as well as the corresponding semantic point if there is. Such a mechanism inherently benefits man-made objects with different part constitutions. The effectiveness of our approach is demonstrated through unsupervised 3D semantic correspondence and shape segmentation.

PDF Details

JBHI Journal 2019 Journal Article

Automated Layer Segmentation of Retinal Optical Coherence Tomography Images Using a Deep Feature Enhanced Structured Random Forests Classifier

Xiaoming Liu
Tianyu Fu
Zhifang Pan
Dong Liu
Wei Hu
Jun Liu
Kai Zhang

Optical coherence tomography (OCT) is a high-resolution and noninvasive imaging modality that has become one of the most prevalent techniques for ophthalmic diagnosis. Retinal layer segmentation is very crucial for doctors to diagnose and study retinal diseases. However, manual segmentation is often a time-consuming and subjective process. In this work, we propose a new method for automatically segmenting retinal OCT images, which integrates deep features and hand-designed features to train a structured random forests classifier. The deep convolutional features are learned from deep residual network. With the trained classifier, we can get the contour probability graph of each layer; finally, the shortest path is employed to achieve the final layer segmentation. The experimental results show that our method achieves good results with the mean layer contour error of 1. 215 pixels, whereas that of the state of the art was 1. 464 pixels, and achieves an F1-score of 0. 885, which is also better than 0. 863 that is obtained by the state of the art method.

Details DOI

AAAI Conference 2019 Short Paper

Deep Reinforcement Learning via Past-Success Directed Exploration

Xiaoming Liu
Zhixiong Xu
Lei Cao
Xiliang Chen
Kai Kang

The balance between exploration and exploitation has always been a core challenge in reinforcement learning. This paper proposes “past-success exploration strategy combined with Softmax action selection”(PSE-Softmax) as an adaptive control method for taking advantage of the characteristics of the online learning process of the agent to adapt exploration parameters dynamically. The proposed strategy is tested on OpenAI Gym with discrete and continuous control tasks, and the experimental results show that PSE-Softmax strategy delivers better performance than deep reinforcement learning algorithms with basic exploration strategies.

PDF Details

AAAI Conference 2019 Conference Paper

Towards Highly Accurate and Stable Face Alignment for High-Resolution Videos

Ying Tai
Yicong Liang
Xiaoming Liu
Lei Duan
Jilin Li
Chengjie Wang
Feiyue Huang
Yu Chen

In recent years, heatmap regression based models have shown their effectiveness in face alignment and pose estimation. However, Conventional Heatmap Regression (CHR) is not accurate nor stable when dealing with high-resolution facial videos, since it finds the maximum activated location in heatmaps which are generated from rounding coordinates, and thus leads to quantization errors when scaling back to the original high-resolution space. In this paper, we propose a Fractional Heatmap Regression (FHR) for high-resolution video-based face alignment. The proposed FHR can accurately estimate the fractional part according to the 2D Gaussian function by sampling three points in heatmaps. To further stabilize the landmarks among continuous video frames while maintaining the precise at the same time, we propose a novel stabilization loss that contains two terms to address time delay and non-smooth issues, respectively. Experiments on 300W, 300- VW and Talking Face datasets clearly demonstrate that the proposed method is more accurate and stable than the state-ofthe-art models.

PDF Details

IS Journal 2017 Journal Article

ACP-Based Management and Control for Urban Passenger Transportation Hubs

Xiaoming Liu
Shaohu Tang
Yuetong Lin
Zhengxi Li
Zhaomeng Chen

Accurate assessment and effective control of urban passenger transportation hub operations are an area that traditional methods have yet to address satisfactorily. This article presents a framework for parallel management and control based on the artificial societies, computational experiments, and parallel execution (ACP) paradigm. The authors first introduce the components, internal interactions, and support mechanism of artificial transportation hubs. They then describe an agent-based model for the hub including the computational experiments and responsibilities of parallel execution in active hub management and control. Thy also present an implementation of the framework through field tests. The framework can improve operational efficiency and service quality of urban passenger transportation hubs.

Details DOI

AIIM Journal 2017 Journal Article

Automatic segmentation of liver tumors from multiphase contrast-enhanced CT images based on FCNs

Changjian Sun
Shuxu Guo
Huimao Zhang
Jing Li
Meimei Chen
Shuzhi Ma
Lanyi Jin
Xiaoming Liu

This paper presents a novel, fully automatic approach based on a fully convolutional network (FCN) for segmenting liver tumors from CT images. Specifically, we designed a multi-channel fully convolutional network (MC-FCN) to segment liver tumors from multiphase contrast-enhanced CT images. Because each phase of contrast-enhanced data provides distinct information on pathological features, we trained one network for each phase of the CT images and fused their high-layer features together. The proposed approach was validated on CT images taken from two databases: 3Dircadb and JDRD. In the case of 3Dircadb, using the FCN, the mean ratios of the volumetric overlap error (VOE), relative volume difference (RVD), average symmetric surface distance (ASD), root mean square symmetric surface distance (RMSD) and maximum symmetric surface distance (MSSD) were 15. 6±4. 3%, 5. 8±3. 5%, 2. 0±0. 9%, 2. 9±1. 5mm, 7. 1±6. 2mm, respectively. For JDRD, using the MC-FCN, the mean ratios of VOE, RVD, ASD, RMSD, and MSSD were 8. 1±4. 5%, 1. 7±1. 0%, 1. 5±0. 7%, 2. 0±1. 2mm, 5. 2±6. 4mm, respectively. The test results demonstrate that the MC-FCN model provides greater accuracy and robustness than previous methods.

Details DOI

AAAI Conference 2014 Conference Paper

On Hair Recognition in the Wild by Machine

Joseph Roth
Xiaoming Liu

We present an algorithm for identity verification using only information from the hair. Face recognition in the wild (i. e. , unconstrained settings) is highly useful in a variety of applications, but performance suffers due to many factors, e. g. , obscured face, lighting variation, extreme pose angle, and expression. It is well known that humans utilize hair for identification under many of these scenarios due to either the consistent hair appearance of the same subject or obvious hair discrepancy of different subjects, but little work exists to replicate this intelligence artificially. We propose a learned hair matcher using shape, color, and texture features derived from localized patches through an AdaBoost technique with abstaining weak classifiers when features are not present in the given location. The proposed hair matcher achieves 71. 53% accuracy on the LFW View 2 dataset. Hair also reduces the error of a Commercial Off-The-Shelf (COTS) face matcher through simple score-level fusion by 5. 7%.

PDF Details