Chi Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chi Zhang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Wei Wang
Beijing Jiaotong University, Beijing, China
3 shared publications - Yao Zhao
Institute of Information Science, Beijing Jiaotong University, Beijing, China and Visual Intelligence + X International Joint Laboratory, Beijing, China
3 shared publications - Bin Wu
Beijing Jiaotong University
1 shared publication Biru Zhu
Henan Key Laboratory of Cyberspace Situation Awareness
1 shared publicationChong Fu
Zhengzhou University
1 shared publication- Nicu Sebe
University of Trento, Trento, Italy
1 shared publication
Latest Publications
- 12 September 2026
- Published by Springer Nature
- p. 445-462
Beyond the Boundary: RL-Driven Solution Space Exploration for Blind Face Restoration
- 12 September 2026
- Published by Springer Nature
- p. 445-462
Beyond the Boundary: RL-Driven Solution Space Exploration for Blind Face Restoration
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 4064-4077
Sharpness-Aware Fine-Tuning for OOD Detection
The out-of-distribution (OOD) detection task is crucial for the real-world deployment of machine learning models. In this paper, we propose to study the problem from the perspective of Sharpness-aware Minimization (SAM). Compared with traditional optimizers such as SGD, SAM can better improve the model performance and generalization ability, and this is closely related to OOD detection [1]. Therefore, instead of using SGD, we propose to fine-tune the model with SAM, and observe that the score distributions of in-distribution (ID) data and OOD data are pushed away from each other. Besides, with our carefully designed loss, the fine-tuning process is very time-efficient. The OOD performance improvement can be observed after fine-tuning the model within 1 epoch. Moreover, our method is very flexible and can be used to improve the performance of different OOD detection methods. Extensive experiments have demonstrated that our method achieves state-of-the-art performance on widely-used OOD benchmarks across different architectures. Moreover, comprehensive ablation studies and theoretical analyses are discussed to support the empirical results.
- 9 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 4064-4077
Sharpness-Aware Fine-Tuning for OOD Detection
The out-of-distribution (OOD) detection task is crucial for the real-world deployment of machine learning models. In this paper, we propose to study the problem from the perspective of Sharpness-aware Minimization (SAM). Compared with traditional optimizers such as SGD, SAM can better improve the model performance and generalization ability, and this is closely related to OOD detection [1]. Therefore, instead of using SGD, we propose to fine-tune the model with SAM, and observe that the score distributions of in-distribution (ID) data and OOD data are pushed away from each other. Besides, with our carefully designed loss, the fine-tuning process is very time-efficient. The OOD performance improvement can be observed after fine-tuning the model within 1 epoch. Moreover, our method is very flexible and can be used to improve the performance of different OOD detection methods. Extensive experiments have demonstrated that our method achieves state-of-the-art performance on widely-used OOD benchmarks across different architectures. Moreover, comprehensive ablation studies and theoretical analyses are discussed to support the empirical results.