Xucong Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xucong Wang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Pengkun Wang
University of Science and Technology of China, Hefei, China
2 shared publications - Liheng Yu
University of Science and Technology of China, Hefei, China
1 shared publication - Miao Fang
School of Computer and Communication Engineering, Northeastern University, Qinhuangdao 066004, China
1 shared publication Shurui Zhang
Northeastern University at Qinhuangdao
1 shared publicationYang Wang
University of Science and Technology of China
1 shared publication- Yang Wang
University of Science and Technology of China, Hefei, China
1 shared publication
Latest Publications
- 17 September 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (10) , 431
LAMP: Long-Tailed Multi-modal Prompt Tuning for Vision-Language Models
- 17 September 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (10) , 431
LAMP: Long-Tailed Multi-modal Prompt Tuning for Vision-Language Models
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (20) , 21330-21338
Multi-label Self Knowledge Distillation
Self-Knowledge Distillation (SKD) leverages the student's own knowledge to create a virtual teacher for distillation when the pre-trained bulky teacher is not available. Whilst existing SKD approaches demonstrate gorgeous efficiency in single-label learning, to directly apply them to multi-label learning would suffer from dramatic degradation due to the following inherent imbalance: \textit{targets with unified labels but multifarious visual scales are crammed into one image, resulting in biased learning of major targets and disequilibrium of precision-recall}. To address this issue, this paper proposes a novel SKD method for multi-label learning named Multi-label Self-knowledge Distillation (MSKD), incorporating three Spatial Decoupling mechanisms (i.e. Locality-SD (L-SD), Reconstruction-SD (R-SD), and Step-SD (S-SD)). L-SD exploits relational dark knowledge from regional outputs to amplify the model's perception of visual details. R-SD reconstructs global semantics by integrating regional outputs from local patches and leverages it to guide the model. S-SD aligns outputs of the same input at different steps, aiming to find a synthetical optimizing direction and avoid the overconfidence. In addition, MSKD combines our tailored loss named MBD for balanced distillation. Exhaustive experiments demonstrate that MSKD not only outperforms previous approaches but also effectively mitigates biased learning and equips the model with more robustness.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (20) , 21330-21338
Open AccessMulti-label Self Knowledge Distillation
Self-Knowledge Distillation (SKD) leverages the student's own knowledge to create a virtual teacher for distillation when the pre-trained bulky teacher is not available. Whilst existing SKD approaches demonstrate gorgeous efficiency in single-label learning, to directly apply them to multi-label learning would suffer from dramatic degradation due to the following inherent imbalance: \textit{targets with unified labels but multifarious visual scales are crammed into one image, resulting in biased learning of major targets and disequilibrium of precision-recall}. To address this issue, this paper proposes a novel SKD method for multi-label learning named Multi-label Self-knowledge Distillation (MSKD), incorporating three Spatial Decoupling mechanisms (i.e. Locality-SD (L-SD), Reconstruction-SD (R-SD), and Step-SD (S-SD)). L-SD exploits relational dark knowledge from regional outputs to amplify the model's perception of visual details. R-SD reconstructs global semantics by integrating regional outputs from local patches and leverages it to guide the model. S-SD aligns outputs of the same input at different steps, aiming to find a synthetical optimizing direction and avoid the overconfidence. In addition, MSKD combines our tailored loss named MBD for balanced distillation. Exhaustive experiments demonstrate that MSKD not only outperforms previous approaches but also effectively mitigates biased learning and equips the model with more robustness.