VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples

TL;DR

VideoMoCo enhances contrastive video representation learning by introducing temporal adversarial augmentation and decay modeling, leading to more robust and effective unsupervised video features without pretext tasks.

Contribution

It proposes a novel temporal adversarial augmentation and decay mechanism to improve unsupervised video representation learning with contrastive methods.

Findings

Achieves state-of-the-art results on UCF101 and HMDB51 datasets.

Improves temporal robustness of video representations.

Outperforms previous unsupervised methods in benchmark evaluations.

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.