Hello! I’m Yunkang Cao (曹云康), a Ph.D. candidate at Huazhong University of Science and Technology (HUST), where I am fortunate to be working under the guidance of Prof. Weiming Shen. Currently, I am visiting Politecnico Milano (Polimi) under the supervision of Giacomo Boracchi.

My academic interests revolve around Deep Learning and Computer Vision, with a specific focus on Multi-modal Anomaly Detection. Lately, my research has been centered on the application of foundational models like vision-language models in anomaly detection tasks, alongside my exploration of Zero/Few-shot Anomaly Detection.

Beyond visual anomaly detection, my long-term goal is to empower intelligent visual systems with reasoning and planning capabilities about anomalies. This approach aims to enable these systems to handle and recover from potential open-world anomalies, thereby achieving better robustness and safety for fields such as intelligent manufacturing and autonomous driving.

If you find my research intriguing, please don’t hesitate to get in touch with me. I welcome any inquiries or discussions regarding my work! 😊

Recently, I have been looking for postdoctoral openings. If you have any opportunities or are interested in collaborating, please feel free to email me!

🔥 News

2024.09: 🎉🎉 Our paper addressed Few-shot Anomaly Detection is accepted by IEEE TNNLS.
2024.09: 🎉🎉 Our paper addressed Logical Anomaly Detection is accepted by IEEE TASE.
2024.08: 🎉🎉 Our paper addressed Knowledge Distillation is accepted by Knowledge-based Systems.
2024.08: 🎉🎉 Our paper addressed Few-shot Image Anomaly Detection is accepted by Knowledge-based Systems.
2024.07: 🎉🎉 Our paper addressed Zero-shot Image Anomaly Detection is accepted by ECCV.
2024.06: 🎉🎉 Our paper addressed Point Cloud Anomaly Detection is accepted by Pattern Recognition.
2024.05: 🎉🎉 Our paper addressed Multi-class Image Anomaly Detection is accepted by IEEE TII.
2024.05: 🎉🎉 Our papers addressed Robust Image Anomaly Detection and Multi-Illumination Image Anomaly Detection are accepted by IEEE CASE.
2024.02: 🎉🎉 We are organizing a special session titled Industrial Foundation Models and Applications in Smart Manufacturing (CODE: ypg7k) in CASE 2024. We welcome contributions!
2023.12: 🎉🎉 Our paper addressed Semi-supervised Image Anomaly Detection is accepted by IEEE Transactions on Instrumentation and Measurement.
2023.12: 🎉🎉 Our paper addressed Semi-supervised Image Anomaly Detection is accepted by IEEE Transactions on Systems, Man, and Cybernetics: Systems.
2023.11: 🎉🎉 We released Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the Lead (Code), the first comprehensive evaluation on GPT-4V for generic anomaly detection. Press Coverage: 机器之心.
2023.09: 🎉🎉 Our paper addressed Unsupervised Image Anomaly Detection is accepted by Knowledge-based Systems.
2023.06: 🎉🎉 We won the 2nd place in CVPR VAND Zero-shot Anomaly Detection Challenge. Press Coverage: 华中科技大学, 我爱计算机视觉.
2023.05: 🎉🎉 We released Segment Any Anomaly without Training via Hybrid Prompt Regularization (Paper) (Code) for zero-shot anomaly segmentation.
2023.05: 🎉🎉 Our paper addressed High-Resolution Image Anomaly Detection has been accepted by IEEE CASE 2023.
2023.03: 🎉🎉 We released Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection for point cloud anomaly detection.
2023.01: 🎉🎉 Our paper addressed Unsupervised Image Anomaly Detection is accepted by IEEE TII.
2022.09: 🎉🎉 One paper is accepted by Knowledge-based Systems.
2022.05: 🎉🎉 One paper is accepted by IEEE CASE 2022.
2022.05: 🎉🎉 We get The Mathematical Modeling Stars Nomination in the 18th China Post-graduate Mathematical Contest.
2022.03: 🎉🎉 Two papers are accepted by IEEE CSCWD 2022.
2022.03: 🎉🎉 Our paper addressed Unsupervised Image Anomaly Detection is accepted by Knowledge-based Systems.

📝 Publications

First-Authored Peer-Reviewed Publications
Other Peer-Reviewed Publications
First-Authored Manuscripts under Review
Other Manuscripts under Review

# co-first author | * corresponding author

First-Authored Peer-Reviewed Publications

AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection [Paper] [Code]
Yunkang Cao, Jiangning Zhang, Luca Frittoli, Yuqi Cheng, Weiming Shen*, Giacomo Boracchi
European Conference on Computer Vision (ECCV). 2024.
Complementary pseudo multimodal feature for point cloud anomaly detection [Paper] [Code]
Yunkang Cao, Xiaohao Xu, Weiming Shen*
Pattern Recognition (PR). 2024.
BiaS: Incorporating Biased Knowledge to Boost Unsupervised Image Anomaly Localization [Paper]
Yunkang Cao, Xiaohao Xu, Chen Sun, Liang Gao, Weiming Shen*
IEEE Transactions on Systems, Man, and Cybernetics: Systems (IEEE TSMC). 2024.
Collaborative discrepancy optimization for reliable image anomaly localization [Paper] [Code]
Yunkang Cao, Xiaohao Xu, Zhaoge Liu, Weiming Shen*
IEEE Transactions on Industrial Informatics (IEEE TII). 2023.
High-Resolution Image Anomaly Detection via Spatiotemporal Consistency Incorporated Knowledge Distillation [Paper]
Yunkang Cao, Yiheng Zhang, Weiming Shen*
IEEE International Conference on Automation Science and Engineering (IEEE CASE). 2023.
Informative knowledge distillation for image anomaly segmentation [Paper] [Code]
Yunkang Cao, Qian Wan, Weiming Shen*, Liang Gao
Knowledge-Based Systems (KBS). 2022.

Other Peer-Reviewed Publications

Prototypical Learning Guided Context-Aware Segmentation Network for Few-Shot Anomaly Detection [Paper] [Code]
Yuxin Jiang, Yunkang Cao, Weiming Shen*
IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS).
LogiCode: an LLM-Driven Framework for Logical Anomaly Detection [Paper] [Code]
Yiheng Zhang, Yunkang Cao, Xiaohao Xu, Weiming Shen*
IEEE Transactions on Automation Science and Engineering (IEEE TASE).
Prior Normality Prompt Transformer for Multi-class Industrial Image Anomaly Detection [Paper]
Haiming Yao, Yunkang Cao, Wei Luo, Weihang Zhang, Wenyong Yu*, Weiming Shen
IEEE Transactions on Industrial Informatics (IEEE TII). 2024.
Deep Feature Contrasting for Industrial Image Anomaly Segmentatio [Paper]
Qian Wan, Yunkang Cao, Liang Gao, Xinyu Li*, Yiping Gao
IEEE Transactions on Instrumentation and Measurement (IEEE TIM). 2024.
Dual-path Frequency Discriminators for Few-shot Anomaly Detection
Yuhu Bai#, Jiangning Zhang#, Zhaofeng Chen, Yuhang Dong, Yunkang Cao, Guanzhong Tian*
Knowledge-Based Systems (KBS). 2024.
Generative Denoise Distillation: Simple Stochastic Noises Induce Efficient Knowledge Transfer for Dense Prediction
Zhaoge Liu, Xiaohao Xu, Yunkang Cao, Weiming Shen*
Knowledge-Based Systems (KBS). 2024.
RAD: A Comprehensive Dataset for Benchmarking the Robustness of Image Anomaly Detection [Paper] [Code]
Yuqi Cheng, Yunkang Cao, Rui Chen, Weiming Shen*
IEEE International Conference on Automation Science and Engineering (IEEE CASE). 2024.
Attention Fusion Reverse Distillation for Multi-Lighting Image Anomaly Detection [Paper]
Yiheng Zhang, Yunkang Cao, Tianhang Zhang, Weiming Shen*
IEEE International Conference on Automation Science and Engineering (IEEE CASE). 2024.
A masked reverse knowledge distillation method incorporating global and local information for image anomaly detection [Paper] [Code]
Yuxin Jiang, Yunkang Cao, Weiming Shen*
Knowledge-Based Systems (KBS). 2023.
Position encoding enhanced feature mapping for image anomaly detection [Paper] [Code]
Qian Wan, Yunkang Cao, Liang Gao, Weiming Shen, Xinyu Li*
IEEE International Conference on Automation Science and Engineering (IEEE CASE). 2022.

First-Authored Manuscripts under Review

A Generalized Medical Anomaly Detection Suite: Detecting Anomalies in Multi-Source and Multi-Modality Images.
Yunkang Cao#, Haiming Yao#, Yu Cai, Hao Chen, Weiming Shen*
IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS). (under review)
Segment any anomaly without training via hybrid prompt regularization [Paper] [Code]
Yunkang Cao, Xiaohao Xu, Chen Sun, Yuqi Cheng, Zongwei Du, Liang Gao, Weiming Shen*
IEEE Transactions on Cybernetics (IEEE TCYB). (major revision)
VarAD: Lightweight High-Resolution Image Anomaly Detection via Visual Autoregressive Modeling
Yunkang Cao, Haiming Yao, Wei Luo, Weiming Shen* (major revision)
A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospect [Paper]
Yunkang Cao, Xiaohao Xu, Jiangning Zhang, Yuqi Cheng, Xiaonan Huang, Guansong Pang, Weiming Shen* (under review)
Towards generic anomaly detection and understanding: Large-scale visual-linguistic model (gpt-4v) takes the lead [Paper] [Code]
Yunkang Cao, Xiaohao Xu, Chen Sun, Xiaonan Huang, Weiming Shen* (under review)
Towards Zero-shot Point Cloud Anomaly Detection: A Multi-View Projection Framework [Paper] [Code]
Yuqi Cheng#, Yunkang Cao#, Guoyang Xie, Zhichao Lu, Weiming Shen*
IEEE Transactions on Systems, Man, and Cybernetics: Systems (IEEE TSMC) . (major revision)

Other Manuscripts under Review

CUT: A Controllable, Universal, and Training-Free Visual Anomaly Generation Framework [Paper]
Han Sun, Yunkang Cao, Olga Fink* (under review)
VTFusion: A Vision-Text Multimodal Fusion Network for Few-Shot Anomaly Detection
Yuxin Jiang, Yunkang Cao, Yuqi Cheng, Yiheng Zhang, Weiming Shen*
IEEE Transactions on Cybernetics (IEEE TCYB). (major revision)
Global-Regularized Neighborhood Regression for Efficient Zero-Shot Texture Anomaly Detection [Paper] [Code]
Haiming Yao, Wei Luo, Yunkang Cao, Yiheng Zhang, Wenyong Yu*, Weiming Shen
IEEE Transactions on Systems, Man, and Cybernetics: Systems (IEEE TSMC). (major revision)
URA-Net: Uncertainty-Integrated Anomaly Perception and Restoration Attention Network for Unsupervised Anomaly Detection
Wei Luo, Peng Xing, Yunkang Cao, Haiming Yao, Weiming Shen, Zechao Li* (under review)

💻 Projects

Mobile E-Ink Screen Surface Defect Detection Equipment Jun. 2023 - Present

constructed a high-resolution defect inspection prototype for mobile e-ink screens.
collected a comprehensive dataset of high-resolution images for mobile e-ink screen inspection.
translated image anomaly detection into token prediction, and introduced state space models to predict the future tokens based on previous tokens.
achieved high detection efficiency with great global information capture capacity for high-resolution images.

Complex Surface Part Inspection Equipment Jun. 2020 - Jun. 2024

constructed a multi-view and multi-illumination defect inspection prototype equipment for curved surface parts.
collected an automotive part inspection dataset featuring multi-illumination images.
proposed a multi-illumination visual anomaly detection task and extended reverse knowledge distillation for this task.
improved 6.5% detection AUROC with minimal additional overhead in comparison to anomaly detection under single illumination.

🥇 Selected Awards

Provincial Second Prize, China International College Students’ Innovation Competition, 2024.08
2nd place in CVPR VAND Zero-shot Anomaly Detection Challenge
First-class Scholarship for Postgraduates, HUST, 2020.09, 2021.09, 2022.09
Student Award for Research and Innovation, HUST, 2022.05
Mathematical Modeling Stars Nomination (TOP 2) in the 18th China Post-graduate Mathematical Contest, 2022.05
Merit Postgraduate student, HUST, 2021.09
Excellent Graduates, HUST, 2019.06
National Scholarship (the highest scholarship for B.E), 2017.09, 2019.09
Second Class Prize, Undergraduate Electronics Design Contest, Provincial, 2018.09
Third Class Prize, Undergraduate Intelligent Robotics Contest, National, 2018.05

🎓📚 Academic Service

Journal Reviewer, IEEE Trans. Syst. Man Cybern. -Syst., IEEE Trans. Neural Netw. Learn. Syst., IEEE Trans. Ind. Inform., IEEE Trans. Circuits Syst. Video Technol., etc.
Conference Reviewer, CVPR, NeurIPS, AAAI, ICRA, etc.
Co-organizer of special sessions, [Anomaly Detection with Foundation Models (ADFM)] at IJCAI (2024).
Co-organizer of special sessions, [Industrial Foundation Models and Applications in Smart Manufacturing] at the IEEE International Conference on Automation Science and Engineering (2024).

💬 Invited Talks

2024.07, EPFL, “Application-Oriented Industrial Visual Anomaly Detection” [Slides].
2023.11, National University of Defense Technology, “Overview of Image Anomaly Detection—Review, Applications, and Future Prospects” [Slides].

📖 Educations

2023.10 - present, Politecnico di Milano

Department of Electronics, Information and Bioengineering
Visiting Ph.D. in Computer Science Advisor: Giacomo Boracchi
2020.09 - present, Huazhong University of Science and Technology

State Key Laboratory of Digital Manufacturing Equipment and Technology
Ph.D. Candidate in Mechanical Engineering Advisor: Weiming Shen
2016.09 - 2020.06, Huazhong University of Science and Technology

B.S. in Mechanical Design, Manufacture & Automation

Yunkang CAO