Class Incremental Learning for Video Action Classification

Jiawei Ma, Xiaoyu Tao, Jianxing Ma, Xiaopeng Hong, Yihong GongICIP 2021 · OpenReview

Abstract

Class Incremental Learning (CIL) is a hot topic in machine learning for CNN models to learn new classes incrementally. However, most of the CIL studies are for image classification and object recognition tasks and few CIL studies are available for video action classification. To mitigate this problem, in this paper, we present a new Grow When Required network (GWR) based video CIL framework for action classification. GWR learns knowledge incrementally by modeling the manifold of video frames for each encountered action class in feature space. We also introduce a Knowledge Consolidation (KC) method to separate the feature manifolds of old class and new class and introduce an associative matrix for label prediction. Experimental results on KTH and Weizmann demonstrate the effectiveness of the framework.
BibTeX
@inproceedings{ma2021class,
  author = {Jiawei Ma and Xiaoyu Tao and Jianxing Ma and Xiaopeng Hong and Yihong Gong},
  title = {{Class Incremental Learning for Video Action Classification}},
  booktitle = {ICIP},
  year = {2021},
  url = {https://openreview.net/forum?id=6Zs6JdxO2LM},
}

Loading related content...

Figure