Inter-intra Variant Dual Representations forSelf-supervised Video Recognition
This work improves self-supervised learning for video recognition, offering gains for researchers and practitioners in computer vision, though it is incremental as it builds on existing contrastive frameworks.
The paper tackles the problem of self-supervised video recognition by addressing the neglect of intra-variance within video clips, proposing dual representations that balance inter- and intra-variance through shuffle-rank and contrastive tasks. It achieves 82.0% and 51.2% classification accuracy on UCF101 and HMDB51, and 46.1% retrieval accuracy on UCF101, outperforming existing methods.
Contrastive learning applied to self-supervised representation learning has seen a resurgence in deep models. In this paper, we find that existing contrastive learning based solutions for self-supervised video recognition focus on inter-variance encoding but ignore the intra-variance existing in clips within the same video. We thus propose to learn dual representations for each clip which (\romannumeral 1) encode intra-variance through a shuffle-rank pretext task; (\romannumeral 2) encode inter-variance through a temporal coherent contrastive loss. Experiment results show that our method plays an essential role in balancing inter and intra variances and brings consistent performance gains on multiple backbones and contrastive learning frameworks. Integrated with SimCLR and pretrained on Kinetics-400, our method achieves $\textbf{82.0\%}$ and $\textbf{51.2\%}$ downstream classification accuracy on UCF101 and HMDB51 test sets respectively and $\textbf{46.1\%}$ video retrieval accuracy on UCF101, outperforming both pretext-task based and contrastive learning based counterparts. Our code is available at \href{https://github.com/lzhangbj/DualVar}{https://github.com/lzhangbj/DualVar}.