Knowledge Commons of Institute of Automation,CAS
Learning Multi-expert Distribution Calibration for Long-tailed Video Classification | |
Hu, Yufan1; Gao, Junyu2,3; Xu, Changsheng2,3,4 | |
发表期刊 | IEEE Transactions on Multimedia |
2023 | |
卷号 | 0期号:0页码:1-13 |
文章类型 | 0 |
摘要 | Most existing state-of-the-art video classification methods assume that the training data obey a uniform distribution. However, video data in the real world typically exhibit an imbalanced long-tailed class distribution, resulting in a model bias towards head class and relatively low performance on tail class. While the current long-tailed classification methods usually focus on image classification, adapting them to video data is not a trivial extension. We propose an end-to-end multi-expert distribution calibration method to address these challenges based on two-level distribution information. The method jointly considers the distribution of samples in each class (intra-class distribution) and the overall distribution of diverse data (inter-class distribution) to solve the issue of imbalanced data under long-tailed distribution. By modeling the two-level distribution information, the model can jointly consider the head classes and the tail classes and significantly transfer the knowledge from the head classes to improve the performance of the tail classes. Extensive experiments verify that our method achieves state-of-the-art performance on the long-tailed video classification task. |
其他摘要 |
|
WOS记录号 | WOS:001157873000001 |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 小样本高噪声数据学习 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51518 |
专题 | 多模态人工智能系统全国重点实验室 |
作者单位 | 1.School of Intelligence and Technology, University of Science and Technology Beijing 2.State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences 3.School of Artificial Intelligence, University of Chinese Academy of Sciences 4.Peng Cheng Laboratory |
推荐引用方式 GB/T 7714 | Hu, Yufan,Gao, Junyu,Xu, Changsheng. Learning Multi-expert Distribution Calibration for Long-tailed Video Classification[J]. IEEE Transactions on Multimedia,2023,0(0):1-13. |
APA | Hu, Yufan,Gao, Junyu,&Xu, Changsheng.(2023).Learning Multi-expert Distribution Calibration for Long-tailed Video Classification.IEEE Transactions on Multimedia,0(0),1-13. |
MLA | Hu, Yufan,et al."Learning Multi-expert Distribution Calibration for Long-tailed Video Classification".IEEE Transactions on Multimedia 0.0(2023):1-13. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论