Inter-intra Variant Dual Representations forSelf-supervised Video Recognition

Abstract

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 $\text{82.0\%}$ and $\text{51.2\%}$ downstream classification accuracy on UCF101 and HMDB51 test sets respectively and $\text{46.1\%}$ 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}.

Accepted by BMVC 2021

References in corpus (9)

• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• Bootstrap your own latent: A new approach to self-supervised Learning
• The Kinetics Human Action Video Dataset
• Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework
• RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning
• Incorporating Intra-Class Variance to Fine-Grained Visual Recognition
• Self-Supervised Ranking for Representation Learning
• TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding
• CatNet: Class Incremental 3D ConvNets for Lifelong Egocentric Gesture Recognition