Class-Incremental Learning for Action Recognition in Videos
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.
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