Author name cluster

Kang Li

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.

18 papers

2 author rows

AAAI Conference 2026 Conference Paper

MaskAD: Parallel Masked Autoencoder for Multi-class Unsupervised Anomaly Detection

Ruiying Lu
Gang Liu
Kang Li
Long Tian
Junwei Zhang

Multi-class unsupervised anomaly detection endeavors to establish a unified model capable of identifying anomalies across multiple classes when only normal data is accessible. However, widely employed reconstruction-based networks often struggle with the 'identical shortcut' issue of both normal and anomalous samples being reconstructed equally well, consequently failing to identify outliers. Although current methodologies attempt to tackle this problem, they remain susceptible to infiltration of anomalous information. In contrast, we introduce a novel scheme to make use of the `identical shortcut' phenomenon rather than pursue to eliminate it. Firstly, inspired by our interesting observation that normal and abnormal regions manifest distinct behaviors when encountering diverse masks, we devise a multi-branch masked autoencoder tailored for multi-class image reconstruction. Subsequently, we introduce a parallel masking scheme to magnify the reconstruction disparity between normal and abnormal regions when confronted with various masks. Ultimately, we propose a reconstruction association discrepancy learning method as a new anomaly localization criterion. The effectiveness of our approach is validated both quantitatively and qualitatively, achieving state-of-the-art results.

PDF Details DOI

AIIM Journal 2025 Journal Article

A cell-interacting and multi-correcting method for automatic circulating tumor cells detection

Xuan Zhang
Rensheng Lai
Ling Bai
Jianxin Ji
Ruihao Qin
Lihong Jiang
Bin Meng
Ying Zhang

Sensitive detection of circulating tumor cells (CTCs) from peripheral blood can serve as an effective tool in the early diagnosis and prognosis of cancer. Many methods based on modern object detectors were proposed in recent years for automatic abnormal cells detection in slide images. Although the modes of these methods can also be applied to the CTCs detection, several practical difficulties lead to suboptimal performance of them, such as accurate capture of CTCs in a large number of mixed cells and identification of CTCs and CTC-like cells with similar visual characteristics. Here, we develop a new cell-interacting and multi-correcting detector called CMD, and apply H&E-stained slide images to detect CTCs automatically for the first time. Specifically, the proposed method incorporates two task-oriented novel modules: (1) a self-attention module for aggregating feature interactions between cells and allowing the model to pay more attention to key abnormal cells, (2) a hard sample mining sampler for progressively correcting predictions of cells with ambiguous classification boundaries. Experiments conducted on a multi-center dataset of 1247 annotated slide images confirm the superiority of our method over state-of-the-art cell detection methods. The results of ablation experiment part also prove the effectiveness of two modules. The source codes of this paper are available at https: //github. com/zx333445/CMD.

Details DOI

ICML Conference 2025 Conference Paper

LOB-Bench: Benchmarking Generative AI for Finance - an Application to Limit Order Book Data

Peer Nagy
Sascha Yves Frey
Kang Li
Bidipta Sarkar
Svitlana Vyetrenko
Stefan Zohren
Anisoara Calinescu
Jakob N. Foerster

While financial data presents one of the most challenging and interesting sequence modelling tasks due to high noise, heavy tails, and strategic interactions, progress in this area has been hindered by the lack of consensus on quantitative evaluation paradigms. To address this, we present LOB-Bench, a benchmark, implemented in python, designed to evaluate the quality and realism of generative message-by-order data for limit order books (LOB) in the LOBSTER format. Our framework measures distributional differences in conditional and unconditional statistics between generated and real LOB data, supporting flexible multivariate statistical evaluation. The benchmark also includes features commonly used LOB statistics such as spread, order book volumes, order imbalance, and message inter-arrival times, along with scores from a trained discriminator network. Lastly, LOB-Bench contains "market impact metrics", i. e. the cross-correlations and price response functions for specific events in the data. We benchmark generative autoregressive state-space models, a (C)GAN, as well as a parametric LOB model and find that the autoregressive GenAI approach beats traditional model classes.

Details

EAAI Journal 2024 Journal Article

Fuzzy graph convolutional network for hyperspectral image classification

Jindong Xu
Kang Li
Ziyi Li
Qianpeng Chong
Haihua Xing
Qianguo Xing
Mengying Ni

—Graph convolutional network (GCN) has attracted much attention in the field of hyperspectral image classification for its excellent feature representation and convolution on arbitrarily structured non-Euclidean data. However, most state-of-the-art methods build a graph utilize the distance measure, which makes it challenging to fully characterize the complex relationship of hyperspectral remote sensing data. Moreover, the hyperspectral image usually has uncertainty introduced by the problems of the spectral variability and noise interference. This article uses fuzzy theory to optimize the GCN and thus solve the uncertainty problem in hyperspectral images, and presents a novel fuzzy graph convolutional network (F-GCN) for hyperspectral image classification. By calculating the fuzzy similarity of samples, a robust graph is first built rather than using the traditional Euclidean distance method, which allows a better representation of the complex relationship between hyperspectral remote sensing data. Furthermore, the proposed network introduces fuzzy layers into the model to cope with the ambiguity of the hyperspectral image. Finally, the classification results for three real-world hyperspectral data sets to show its feasibility and effectiveness in hyperspectral image classification.

Details DOI

AIIM Journal 2024 Journal Article

Healthcare facilities management: A novel data-driven model for predictive maintenance of computed tomography equipment

Haopeng Zhou
Qilin Liu
Haowen Liu
Zhu Chen
Zhenlin Li
Yixuan Zhuo
Kang Li
Changxi Wang

Background The breakdown of healthcare facilities is a huge challenge for hospitals. Medical images obtained by Computed Tomography (CT) provide information about the patients' physical conditions and play a critical role in diagnosis of disease. To deliver high-quality medical images on time, it is essential to minimize the occurrence frequencies of anomalies and failures of the equipment. Methods We extracted the real-time CT equipment status time series data such as oil temperature, of three equipment, between May 19, 2020, and May 19, 2021. Tube arcing is treated as the classification label. We propose a dictionary-based data-driven model SAX-HCBOP, where the two methods, Histogram-based Information Gain Binning (HIGB) and Coefficient improved Bag of Pattern (CoBOP), are implemented to transform the data into the bag-of-words paradigm. We compare our model to the existing predictive maintenance models based on statistical and time series classification algorithms. Results The results show that the Accuracy, Recall, Precision and F1-score of the proposed model achieve 0. 904, 0. 747, 0. 417, 0. 535, respectively. The oil temperature is identified as the most important feature. The proposed model is superior to other models in predicting CT equipment anomalies. In addition, experiments on the public dataset also demonstrate the effectiveness of the proposed model. Conclusions The two proposed methods can improve the performance of the dictionary-based time series classification methods in predictive maintenance. In addition, based on the proposed real-time anomaly prediction system, the model assists hospitals in making accurate healthcare facilities maintenance decisions.

Details DOI

AAAI Conference 2024 Conference Paper

Memory-Efficient Prompt Tuning for Incremental Histopathology Classification

Yu Zhu
Kang Li
Lequan Yu
Pheng Ann Heng

Recent studies have made remarkable progress in histopathology classification. Based on current successes, contemporary works proposed to further upgrade the model towards a more generalizable and robust direction through incrementally learning from the sequentially delivered domains. Unlike previous parameter isolation based approaches that usually demand massive computation resources during model updating, we present a memory-efficient prompt tuning framework to cultivate model generalization potential in economical memory cost. For each incoming domain, we reuse the existing parameters of the initial classification model and attach lightweight trainable prompts into it for customized tuning. Considering the domain heterogeneity, we perform decoupled prompt tuning, where we adopt a domain-specific prompt for each domain to independently investigate its distinctive characteristics, and one domain-invariant prompt shared across all domains to continually explore the common content embedding throughout time. All domain-specific prompts will be appended to the prompt bank and isolated from further changes to prevent forgetting the distinctive features of early-seen domains. While the domain-invariant prompt will be passed on and iteratively evolve by style-augmented prompt refining to improve model generalization capability over time. In specific, we construct a graph with existing prompts and build a style-augmented graph attention network to guide the domain-invariant prompt exploring the overlapped latent embedding among all delivered domains for more domain-generic representations. We have extensively evaluated our framework with two histopathology tasks, i.e., breast cancer metastasis classification and epithelium-stroma tissue classification, where our approach yielded superior performance and memory efficiency over the competing methods.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection

Yiyue Li
Shaoting Zhang
Kang Li
Qicheng Lao

Traditional Anomaly Detection (AD) methods have predominantly relied on unsupervised learning from extensive normal data. Recent AD methods have evolved with the advent of large pre-trained vision-language models, enhancing few-shot anomaly detection capabilities. However, these latest AD methods still exhibit limitations in accuracy improvement. One contributing factor is their direct comparison of a query image's features with those of few-shot normal images. This direct comparison often leads to a loss of precision and complicates the extension of these techniques to more complex domains—an area that remains underexplored in a more refined and comprehensive manner. To address these limitations, we introduce the anomaly personalization method, which performs a personalized one-to-normal transformation of query images using an anomaly-free customized generation model, ensuring close alignment with the normal manifold. Moreover, to further enhance the stability and robustness of prediction results, we propose a triplet contrastive anomaly inference strategy, which incorporates a comprehensive comparison between the query and generated anomaly-free data pool and prompt information. Extensive evaluations across eleven datasets in three domains demonstrate our model's effectiveness compared to the latest AD methods. Additionally, our method has been proven to transfer flexibly to other AD methods, with the generated image data effectively improving the performance of other AD methods.

PDF Details DOI

JBHI Journal 2024 Journal Article

Synthesizing Feature-Aligned and Category-Aware Electronic Medical Records for Intracranial Aneurysm Rupture Prediction

Qian Yang
Caizi Li
Chubin Ou
Kang Li
Xiangyun Liao
Chuanzhi Duan
Lequan Yu
Weixin Si

Rupture prediction is crucial for precise treatment and follow-up management of patients with intracranial aneurysms (IAs). Considerable machine learning (ML) methods have been proposed to improve rupture prediction by leveraging electronic medical records (EMRs), however, data scarcity and category imbalance strongly influence performance. Thus, we propose a novel data synthesis method i. e. , Transformer-based conditional GAN (TransCGAN), to synthesize highly authentic and category-aware EMRs to address above challenges. Specifically, we first align feature-wise context relationship and distribution between synthetic and original data to enhance synthetic data quality. To achieve this, we first integrate the Transformer structure into GAN to match the contextual relationship by processing the long-range dependencies among clinical factors and introduce a statistical loss to maintain distributional consistency by constraining the mean and variance of the synthesis features. Additionally, a conditional module is designed to assign the category of the synthesis data, thereby addressing the challenge of category imbalance. Subsequently, the synthetic data are merged with the original data to form a large-scale and category-balanced training dataset for IAs rupture prediction. Experimental results show that using TransCGAN's synthetic data enhances classifier performance, achieving AUC of 0. 89 and outperforming state-of-the-art resampling methods by 5 $\%$ –33 $\%$ in F1 score.

Details DOI

JBHI Journal 2023 Journal Article

Anatomically Guided Cross-Domain Repair and Screening for Ultrasound Fetal Biometry

Jun Gao
Qicheng Lao
Paul Liu
Huahui Yi
Qingbo Kang
Zekun Jiang
Xiaohu Wu
Kang Li

Ultrasound based estimation of fetal biometry is extensively used to diagnose prenatal abnormalities and to monitor fetal growth, for which accurate segmentation of the fetal anatomy is a crucial prerequisite. Although deep neural network-based models have achieved encouraging results on this task, inevitable distribution shifts in ultrasound images can still result in severe performance drop in real world deployment scenarios. In this article, we propose a complete ultrasound fetal examination system to deal with this troublesome problem by repairing and screening the anatomically implausible results. Our system consists of three main components: A routine segmentation network, a fetal anatomical key points guided repair network, and a shape-coding based selective screener. Guided by the anatomical key points, our repair network has stronger cross-domain repair capabilities, which can substantially improve the outputs of the segmentation network. By quantifying the distance between an arbitrary segmentation mask to its corresponding anatomical shape class, the proposed shape-coding based selective screener can then effectively reject the entire implausible results that cannot be fully repaired. Extensive experiments demonstrate that our proposed framework has strong anatomical guarantee and outperforms other methods in three different cross-domain scenarios.

Details DOI

JBHI Journal 2023 Journal Article

MSA-GCN: A Multi-information Selection Aggregation Graph Convolutional Network for Breast Tumor Grading

Kang Li
Suya Han
Lei Yang
Zizhao Sun
Zhan Yu
Hongwei Xu
Ling Ma
Jianbo Gao

Physicians typically combine multi-modal data to make a graded diagnosis of breast tumors. However, most existing breast tumor grading methods rely solely on image information, resulting in limited accuracy in grading. This paper proposes a Multi-information Selection Aggregation Graph Convolutional Networks (MSA-GCN) for breast tumor grading. Firstly, to fully utilize phenotypic data reflecting the clinical and pathological characteristics of tumors, an automatic combination screening and weight encoder is proposed for phenotypic data, which can construct a population graph with improved structural information. Then, a graph structure is designed through similarity learning to reflect the correlation between patient image features. Finally, a multi-information selection aggregation mechanism is employed in the graph convolution model to extract the effective features of multi-modal data and enhance the classification performance of the model. The proposed method is evaluated on different clinical datasets from the Digital Database for Screening Mammography (DDSM) and INbreast. The average classification accuracies are 90. 74% and 85. 35%, respectively, surpassing the performance of existing methods. In conclusion, our method effectively fuses image and non-image information, leading to a significant improvement in the accuracy of breast tumor grading.

Details DOI

AAMAS Conference 2023 Conference Paper

User Device Interaction Prediction via Relational Gated Graph Attention Network and Intent-aware Encoder

Jingyu Xiao
Qingsong Zou
Qing Li
Dan Zhao
Kang Li
Wenxin Tang
Runjie Zhou
Yong Jiang

With the booming of smart home market, intelligent Internet of Things (IoT) devices have been increasingly more involved in home life. To improve the user experience of smart home, some prior works have explored how to use time series analysis technology for predicting the interaction between users and devices. However, existing solutions have inferior User Device Interaction (UDI) prediction accuracy, as they fail to consider the complex heterogeneous device transitions, multiple intents of a user and multi-level periodicity of user behaviors. In this paper, we present DeepUDI, a novel approach for accurate UDI prediction. First, we propose Relational Gated Graph Attention Network (RGGAT) to learn embedding of device and device control while considering complex heterogeneous temporal transitions. Second, we propose Intent-aware Encoder (IAE) to encode multiple intents of users via capsule networks. Third, we design a Historical Attention Mechanism (HAM) to capture the multi-level periodicity by aggregating the current sequence and the historical sequence representations through the attention mechanism. Comprehensive experiments on four realworld datasets show that DeepUDI consistently outperforms stateof-the-art baselines and also offers highly interpretable results.

PDF

ICRA Conference 2022 Conference Paper

Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking

Longlong Jing
Ruichi Yu
Henrik Kretzschmar
Kang Li
Charles R. Qi
Hang Zhao 0021
Alper Ayvaci
Xu Chen

Monocular image-based 3D perception has become an active research area in recent years owing to its applications in autonomous driving. Approaches to monocular 3D perception including detection and tracking, however, often yield inferior performance when compared to LiDAR-based techniques. Through systematic analysis, we identified that per-object depth estimation accuracy is a major factor bounding the performance. Motivated by this observation, we propose a multi-level fusion method that combines different representations (RGB and pseudo-LiDAR) and temporal information across multiple frames for objects (tracklets) to enhance per-object depth estimation. Our proposed fusion method achieves the state-of-the-art performance of per-object depth estimation on the Waymo Open Dataset, the KITTI detection dataset, and the KITTI MOT dataset. We further demonstrate that by simply replacing estimated depth with fusion-enhanced depth, we can achieve significant improvements in monocular 3D perception tasks, including detection and tracking.

Details

JBHI Journal 2022 Journal Article

HMRNet: High and Multi-Resolution Network With Bidirectional Feature Calibration for Brain Structure Segmentation in Radiotherapy

Hao Fu
Guotai Wang
Wenhui Lei
Wei Xu
Qianfei Zhao
Shichuan Zhang
Kang Li
Shaoting Zhang

Accurate segmentation of Anatomical brain Barriers to Cancer spread (ABCs) plays an important role for automatic delineation of Clinical Target Volume (CTV) of brain tumors in radiotherapy. Despite that variants of U-Net are state-of-the-art segmentation models, they have limited performance when dealing with ABCs structures with various shapes and sizes, especially thin structures (e. g. , the falx cerebri) that span only few slices. To deal with this problem, we propose a High and Multi-Resolution Network (HMRNet) that consists of a multi-scale feature learning branch and a high-resolution branch, which can maintain the high-resolution contextual information and extract more robust representations of anatomical structures with various scales. We further design a Bidirectional Feature Calibration (BFC) block to enable the two branches to generate spatial attention maps for mutual feature calibration. Considering the different sizes and positions of ABCs structures, our network was applied after a rough localization of each structure to obtain fine segmentation results. Experiments on the MICCAI 2020 ABCs challenge dataset showed that: 1) Our proposed two-stage segmentation strategy largely outperformed methods segmenting all the structures in just one stage; 2) The proposed HMRNet with two branches can maintain high-resolution representations and is effective to improve the performance on thin structures; 3) The proposed BFC block outperformed existing attention methods using monodirectional feature calibration. Our method won the second place of ABCs 2020 challenge and has a potential for more accurate and reasonable delineation of CTV of brain tumors.

Details DOI

JBHI Journal 2022 Journal Article

Learning COVID-19 Pneumonia Lesion Segmentation From Imperfect Annotations via Divergence-Aware Selective Training

Shuojue Yang
Guotai Wang
Hui Sun
Xiangde Luo
Peng Sun
Kang Li
Qijun Wang
Shaoting Zhang

Automatic segmentation of COVID-19 pneumonia lesions is critical for quantitative measurement for diagnosis and treatment management. For this task, deep learning is the state-of-the-art method while requires a large set of accurately annotated images for training, which is difficult to obtain due to limited access to experts and the time-consuming annotation process. To address this problem, we aim to train the segmentation network from imperfect annotations, where the training set consists of a small clean set of accurately annotated images by experts and a large noisy set of inaccurate annotations by non-experts. To avoid the labels with different qualities corrupting the segmentation model, we propose a new approach to train segmentation networks to deal with noisy labels. We introduce a dual-branch network to separately learn from the accurate and noisy annotations. To fully exploit the imperfect annotations as well as suppressing the noise, we design a Divergence-Aware Selective Training (DAST) strategy, where a divergence-aware noisiness score is used to identify severely noisy annotations and slightly noisy annotations. For severely noisy samples we use an regularization through dual-branch consistency between predictions from the two branches. We also refine slightly noisy samples and use them as supplementary data for the clean branch to avoid overfitting. Experimental results show that our method achieves a higher performance than standard training process for COVID-19 pneumonia lesion segmentation when learning from imperfect labels, and our framework outperforms the state-of-the-art noise-tolerate methods significantly with various clean label percentages.

Details DOI

IJCAI Conference 2022 Conference Paper

MMT: Multi-way Multi-modal Transformer for Multimodal Learning

Jiajia Tang
Kang Li
Ming Hou
Xuanyu Jin
Wanzeng Kong
Yu Ding
Qibin Zhao

The heart of multimodal learning research lies the challenge of effectively exploiting fusion representations among multiple modalities. However, existing two-way cross-modality unidirectional attention could only exploit the intermodal interactions from one source to one target modality. This indeed fails to unleash the complete expressive power of multimodal fusion with restricted number of modalities and fixed interactive direction. In this work, the multiway multimodal transformer (MMT) is proposed to simultaneously explore multiway multimodal intercorrelations for each modality via single block rather than multiple stacked cross-modality blocks. The core idea of MMT is the multiway multimodal attention, where the multiple modalities are leveraged to compute the multiway attention tensor. This naturally benefits us to exploit comprehensive many-to-many multimodal interactive paths. Specifically, the multiway tensor is comprised of multiple interconnected modality-aware core tensors that consist of the intramodal interactions. Additionally, the tensor contraction operation is utilized to investigate intermodal dependencies between distinct core tensors. Essentially, our tensor-based multiway structure allows for easily extending MMT to the case associated with an arbitrary number of modalities. Taking MMT as the basis, the hierarchical network is further established to recursively transmit the low-level multiway multimodal interactions to high-level ones. The experiments demonstrate that MMT can achieve state-of-the-art or comparable performance.

PDF Details DOI

AAAI Conference 2020 Conference Paper

Towards Cross-Modality Medical Image Segmentation with Online Mutual Knowledge Distillation

Kang Li
Lequan Yu
Shujun Wang
Pheng-Ann Heng

The success of deep convolutional neural networks is partially attributed to the massive amount of annotated training data. However, in practice, medical data annotations are usually expensive and time-consuming to be obtained. Considering multi-modality data with the same anatomic structures are widely available in clinic routine, in this paper, we aim to exploit the prior knowledge (e. g. , shape priors) learned from one modality (aka. , assistant modality) to improve the segmentation performance on another modality (aka. , target modality) to make up annotation scarcity. To alleviate the learning dif- ﬁculties caused by modality-speciﬁc appearance discrepancy, we ﬁrst present an Image Alignment Module (IAM) to narrow the appearance gap between assistant and target modality data. We then propose a novel Mutual Knowledge Distillation (MKD) scheme to thoroughly exploit the modality-shared knowledge to facilitate the target-modality segmentation. To be speciﬁc, we formulate our framework as an integration of two individual segmentors. Each segmentor not only explicitly extracts one modality knowledge from corresponding annotations, but also implicitly explores another modality knowledge from its counterpart in mutual-guided manner. The ensemble of two segmentors would further integrate the knowledge from both modalities and generate reliable segmentation results on target modality. Experimental results on the public multi-class cardiac segmentation data, i. e. , MM- WHS 2017, show that our method achieves large improvements on CT segmentation by utilizing additional MRI data and outperforms other state-of-the-art multi-modality learning methods.

PDF Details

IROS Conference 2017 Conference Paper

The interaction test between a robotic rat and living rat is considered as a possible way to quantitatively characterize the rat sociality. In such robot-rat interactions, the robot should be designed to fully replicate a real rat in terms of morphological and behavioral characteristics. To address this problem, a multi-jointed robot prototype has been modified based on our previous work. We optimally update the forelimb of the robot and redesign the control board to make it more dexterous and increase its behavioral capability. Then, we systematically and kinematically analyze the rotational range of joint variables and the workspace of the robot by using traversal method. To evaluate the motion capability of the modified robot, we propose two quantitative parameters: maximum reachable height (MRH) and minimum bendable distance (MBD). Additionally, we achieve to quantitatively evaluate the behavioral similarity between the robot and rat with the calculated accumulative distance (AD) by using dynamic time warping (DTW). These evaluated methods show high promise to improve the robot-rat interaction to be more similar to rat-rat interaction.

Details

ICRA Conference 2010 Conference Paper

Design and validation of a multi-finger sensing device based on Optical linear encoder

Kang Li
I-Ming Chen 0001
Song Huat Yeo

This paper presents the design and validation of a wearable glove-based multi-finger motion capture device (SmartGlove) with a specific focus on the development of a new optical linear encoder (OLE). The OLE specially designed for this project has a compact size, light weight and low power consumption. The characterization tests also show that the OLE's digital output has good linearity and accuracy. The first prototype of SmartGlove which uses ten OLEs to capture the flexion/extension motion of the 14 finger joints is constructed based on the multi-point sensing method. A user study for the evaluation of SmartGlove using a standard protocol shows high repeatability and reliability in both the gripped and flat hand positions compared with four other evaluated data gloves using the same protocol.

Details