I am Haoyang He (何昊阳). I’m currently pursuing my Ph.D. degree at Zhejiang University in China and expect to graduate in 2027. My advisor is Professor Lei Xie. Currently, I’m interning at Tencent YouTu Lab, Shanghai, mentored by Researcher Jiangning Zhang.
My main research interest is Anomaly Detection. In the past I have used diffusion models (DiAD) as well as Mamba models (MambaAD) for multi-class anomaly detection.
🔥 News
- 2024.10: 🔥🔥🔥Our MambaAD has been accepted by NeurIPS’24. First to use Mamba models to solve Multi-Class Anomaly Detection tasks.
📝 Publications
* means equal contribution.
2024
Learning Multi-view Anomaly Detection,
Haoyang He, Jiangning Zhang, Guanzhong Tian, Lei Xie
(arxiv.) The first attempt for multi-view anomaly detection. [Paper]
ADer: A Comprehensive Benchmark for Multi-class Visual Anomaly Detection,
Jiangning Zhang*, Haoyang He*, Zhenye Gan, Qingdong He, Yuxuan Cai, Zhucun Xue, Yabiao Wang, Chengjie Wang, Lei Xie, Yong Liu
(arxiv.) A comprehensive library for benchmarking multi-class visual anomaly detection. [Paper] | [Code]
MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection,
Haoyang He*, Yuhu Bai*, Jiangning Zhang, Qingdong He, Hongxu Chen, Zhenye Gan, Chengjie Wang, Xiangtai Li, Guanzhong Tian, Lei Xie
(NeurIPS). 2024. The first Mamba model for multi-class anomaly detection. [Paper] | [Code] | [Project]
DiAD: A Diffusion-Based Framework for Multi-Class Anomaly Detection,
Haoyang He*, Jiangning Zhang*, Hongxu Chen, Xuhai Chen, Zhishan Li, Xu Chen, Yabiao Wang, Chengjie Wang, Lei Xie
(AAAI). 2024. The first Diffusion model for multi-class anomaly detection. [Paper] | [Code] | [Project]
2023
GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection,
Jiangning Zhang*, Haoyang He*, Xuhai Chen, Zhucun Xue, Yabiao Wang, Chengjie Wang, Lei Xie, Yong Liu
(IJCAI'24-ADFM) [Paper] | [Code]
Clip-ad: A language-guided staged dual-path model for zero-shot anomaly detection,
Xuhai Chen, Jiangning Zhang, Guanzhong Tian, Haoyang He, Wuhao Zhang, Yabiao Wang, Chengjie Wang, Yunsheng Wu, Yong Liu
(IJCAI'24-ADFM) [Paper] | [Code]
Towards accurate dense pedestrian detection via occlusion-prediction aware label assignment and hierarchical-NMS,
Haoyang He, Zhishan Li, Guanzhong Tian, Hongxu Chen, Lei Xie, Shan Lu, Hongye Su
PRL. [Paper]
🎖 Honors and Awards
- National Scholarship, Ministry of Education of China in SWJTU (year 2020-2021).
- 2022 Sichuan Excellent Graduates.
📖 Educations
- 2022.09 - now, Pursuing Ph.D. College of Control Science and Engineering, Zhejiang University, Hangzhou, China.
- 2018.09 - 2022.06, Obtained B.S. in SWJTU-Leeds Joint School, Southwest Jiaotong University, Chengdu, China.
💻 Internships
- 2024.03 - Now, YouTu Lab, Tencent, Shanghai, mentored by Researcher Jiangning Zhang.