English

Class-Incremental Learning for Action Recognition in Videos

Computer Vision and Pattern Recognition 2022-03-28 v1

Abstract

We tackle catastrophic forgetting problem in the context of class-incremental learning for video recognition, which has not been explored actively despite the popularity of continual learning. Our framework addresses this challenging task by introducing time-channel importance maps and exploiting the importance maps for learning the representations of incoming examples via knowledge distillation. We also incorporate a regularization scheme in our objective function, which encourages individual features obtained from different time steps in a video to be uncorrelated and eventually improves accuracy by alleviating catastrophic forgetting. We evaluate the proposed approach on brand-new splits of class-incremental action recognition benchmarks constructed upon the UCF101, HMDB51, and Something-Something V2 datasets, and demonstrate the effectiveness of our algorithm in comparison to the existing continual learning methods that are originally designed for image data.

Keywords

Cite

@article{arxiv.2203.13611,
  title  = {Class-Incremental Learning for Action Recognition in Videos},
  author = {Jaeyoo Park and Minsoo Kang and Bohyung Han},
  journal= {arXiv preprint arXiv:2203.13611},
  year   = {2022}
}

Comments

12 pages, ICCV 2021

R2 v1 2026-06-24T10:25:50.895Z