VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples

Abstract

MoCo is effective for unsupervised image representation learning. In this paper, we propose VideoMoCo for unsupervised video representation learning. Given a video sequence as an input sample, we improve the temporal feature representations of MoCo from two perspectives. First, we introduce a generator to drop out several frames from this sample temporally. The discriminator is then learned to encode similar feature representations regardless of frame removals. By adaptively dropping out different frames during training iterations of adversarial learning, we augment this input sample to train a temporally robust encoder. Second, we use temporal decay to model key attenuation in the memory queue when computing the contrastive loss. As the momentum encoder updates after keys enqueue, the representation ability of these keys degrades when we use the current input sample for contrastive learning. This degradation is reflected via temporal decay to attend the input sample to recent keys in the queue. As a result, we adapt MoCo to learn video representations without empirically designing pretext tasks. By empowering the temporal robustness of the encoder and modeling the temporal decay of the keys, our VideoMoCo improves MoCo temporally based on contrastive learning. Experiments on benchmark datasets including UCF101 and HMDB51 show that VideoMoCo stands as a state-of-the-art video representation learning method.

arXiv commentCVPR 2021

References in corpus (8)

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• The Kinetics Human Action Video Dataset
• Unsupervised Learning of Video Representations using LSTMs
• Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction
• Video Representation Learning with Visual Tempo Consistency
• Self-supervised Video Representation Learning by Pace Prediction
• Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning

Cited by in corpus (6)

• TCLR: Temporal Contrastive Learning for Video Representation
• Self-Supervised Learning for Videos: A Survey
• Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning
• IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking
• Video Contrastive Learning with Global Context
• Overcoming the Domain Gap in Contrastive Learning of Neural Action Representations