Fang Wan, Assistant Professor
Fang Wan is an assistant professor of University of Chinese Academy of Sciences, supervisor of doctoral students, winner of innovative Postdoctoral Talent Support Program, and excellent doctoral thesis of University of Chinese Academy of Sciences. His research direction is computer vision, focusing on object perception methods with incomplete supervision, such as weakly supervised object detection, active learning object detection, etc. He has published more than 20 international conference/journal papers including IEEE CVPR, ICCV, NeurIPS, AAAI, ECCV and TPAMI, TNNLS, TIP, TCSVT, PR, TGRS. He has won the first prize of Natural Science Award of Chinese Society of Electronics, President's Award of Chinese Academy of Sciences. He achieved the youth Fund of National Natural Science Foundation of China, and scientific research project of Huawei Noah's Ark Laboratory, and participated in 5 national Natural Science Key and general projects.
Research Areas
Computer vision
Machine learning with incomplete supervision
Visual object detection
Experience
2021.12--now UCAS, Assistant Professor
2019.07--2021.12 UCAS, Post-doctoral
2019.03--2019.06 MSRA, Intern
2016.09--2019.06 UCAS Ph.D.
2013.09--2016.06 UCAS, Master's Degree
2009.09--2013.06 Wuhan University, Bachelor's Degree
Publications
Papers
1. Fang Wan, Pengxu Wei, Jianbin Jiao, Zhenjun Han and Qixiang Ye. Min-Entropy Latent Model for Weakly Supervised Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019 (CCF Class A，IF 17.86)
2. Wei Gao, Fang Wan*, Jun Yue, Songcen Xu, Qixiang Ye. Discrepant Multiple Instance Learning for Weakly Supervised Object Detection. Pattern Recognition, 2021（IF：8.793）
3. Wei Gao, Fang Wan*, Xingjia Pan, Zhiliang Peng, Qi Tian, Zhenjun Han, Bolei Zhou, Qixiang Ye*. TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization. IEEE International Conference on Computer Vision (ICCV), 2021. (CCF Class A)
4. Qixiang Ye, Fang Wan*, Chang Liu, Qingming Huang, Xiangyang Ji. (2021). Continuation Multiple Instance Learning for Weakly and Fully Supervised Object Detection. IEEE Transactions on Neural Networks and Learning Systems (TNNLS). Early Access, 1-15. （IF：8.793）
5. Boyu Yang, Fang Wan*, Chang Liu, Bohao Li, Xiangyang Ji, Qixiang Ye. (2021). Part-Based Semantic Transform for Few-Shot Semantic Segmentation. IEEE Transactions on Neural Networks and Learning Systems (TNNLS). Early Access, 1-15.
6. Fang Wan, Chang Liu, Wei Ke, Xiangyang Ji, Jianbin Jiao and Qixiang Ye. C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, 2019 (CCF Class A, Oral)
7. Fang Wan, Pengxu Wei, Jianbin Jiao, Zhenjun Han and Qixiang Ye. Min-Entropy Latent Model for Weakly Supervised Object Detection. International Conference on Computer Vision and Pattern Recognition (CVPR), 2018 (CCF Class A)
8. Tianning Yuan, Fang Wan*, Mengying Fu, Jianzhuang Liu, Songcen Xu, Xiangyang Ji and Qixiang Ye*. (2021). Multiple Instance Active Learning for Object Detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). (CCF Class A)
9. Mengying Fu, Tianning Yuan, Fang Wan*, Songcen Xu, and Qixiang Ye*. Agreement-Discrepancy-Selection: Active Learning with Progressive Distribution Alignment. Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021 (CCF Class A)
10. Zhekun Luo, Devin Guillory, Baifeng Shi, Wei Ke, Fang Wan, Trevor Darrell, Huijuan Xu, Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning, European Conference on Computer Vision, (ECCV) 2020 (CCF Class A)
11. Haolan Xue, Chang Liu, Fang Wan*, Jianbin Jiao, Qixiang Ye*.DANet: Divergent Activation for Weakly Supervised Object Localization. IEEE International Conference on Computer Vision (ICCV), 2019. (CCF Class A)
12. Xiaosong Zhang, Fang Wan, Chang Liu, Xiangyang Ji and Qixiang Ye*, Learning to Match Anchors for Visual Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021
13. Fang Wan, Pengxu Wei, Zhenjun Han, Kun Fu, Qixiang Ye. Weakly Supervised Object Detection with Correlation and Part Suppression. International Conference on Image Processing (ICIP), 2016 (CCF Class C)
14. Xiaosong Zhang, Fang Wan, Chang Liu, Rongrong Ji and Qixiang Ye. FreeAnchor: Learning to Match Anchors for Visual Object Detection. Neural Information Processing Systems (NeurIPS), 2019 (CCF Class A)
15. Chang Liu, Fang Wan, Wei Ke, Zhuowei Xiao, Yuan Yao, Xiaosong Zhang, Qixiang Ye. Orthogonal Decomposition Network for Pixel-wise Binary Classification. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, 2019 (CCF Class A)
16. Caijing Miao, Lingxi Xie, Fang Wan, Chi Su, Hongye Liu, Jianbin Jiao, Qixiang Ye. SIXray: A Large-scale Security Inspection X-ray Benchmark for Prohibited Item Discovery in Overlapping Images. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, 2019 (CCF Class A)
17. Yan Gao, Boxiao Liu, Nan Guo, Xiaochun Ye, Fang Wan, Haihang You, and Dongrui Fan. C-MIDN: Coupled Multiple Instance Detection Network with Segmentation Guidance for Weakly Supervised Object Detection. IEEE International Conference on Computer Vision (ICCV), 2019. (CCF Class A)
18. Chang Liu, Dezhao Luo, Yifei Zhang, Wei Ke, Fang Wan and Qixiang Ye. Parametric Skeleton Generation via Gaussian Mixture Models. IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), Long Beach, USA, 2019 (CCF Class A)
19. Penxu Wei, Fei Qin, Fang Wan, Yi Zhu, Jianbin Jiao and Qixiang Ye. Correlated Topic Vector for Scene Classification, IEEE Transactions on Image Processing, (TIP) 26 (7): 3221 – 3234, 2017.
20. Ke Wei, Tianliang Zhang, Jie Chen, Fang Wan, Qixiang Ye. Texture Complexity based Redundant Regions Re-ranking for Object Proposal, International Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2016 (CCF Class A Workshop)
21. Jialing Zou, Qixiang Ye, Yanting Cui, Fang Wan, Fu Kun, Jianbin Jiao. Collective Motion Pattern Inference via Locally Consistent Latent Dirichlet Allocation[J]. Neurocomputing, 2016, 184:221-231.