no code implementations • 30 Jun 2021 • Hanbin Zhao, Xin Qin, Shihao Su, Yongjian Fu, Zibo Lin, Xi Li
With the rapid development of social media, tremendous videos with new classes are generated daily, which raise an urgent demand for video classification methods that can continuously update new classes while maintaining the knowledge of old videos with limited storage and computing resources.
no code implementations • 4 Aug 2020 • Hanbin Zhao, Hui Wang, Yongjian Fu, Fei Wu, Xi Li
To cope with the forgetting problem, many CIL methods transfer the knowledge of old classes by preserving some exemplar samples into the size-constrained memory buffer.
no code implementations • 24 Jul 2020 • Hanbin Zhao, Hao Zeng, Xin Qin, Yongjian Fu, Hui Wang, Bourahla Omar, Xi Li
As an important and challenging problem, multi-domain learning (MDL) typically seeks for a set of effective lightweight domain-specific adapter modules plugged into a common domain-agnostic network.
no code implementations • 28 Jun 2020 • Hanbin Zhao, Yongjian Fu, Mintong Kang, Qi Tian, Fei Wu, Xi Li
As a challenging problem, few-shot class-incremental learning (FSCIL) continually learns a sequence of tasks, confronting the dilemma between slow forgetting of old knowledge and fast adaptation to new knowledge.
no code implementations • 27 Apr 2020 • Yongjian Fu, Xintian Wu, Xi Li, Zhijie Pan, Daxin Luo
Different from many other attributes, facial expression can change in a continuous way, and therefore, a slight semantic change of input should also lead to the output fluctuation limited in a small scale.
1 code implementation • 18 Apr 2020 • Li Chen, Zewei Xu, Yongjian Fu, Haozhe Huang, Shaowen Wang, Haifeng Li
The incorporation of the double self-attention module has an average of 7\% improvement on the pre-class accuracy.