Learning Cross-modal Contrastive Features for Video Domain Adaptation

Abstract

Learning transferable and domain adaptive feature representations from videos is important for video-relevant tasks such as action recognition. Existing video domain adaptation methods mainly rely on adversarial feature alignment, which has been derived from the RGB image space. However, video data is usually associated with multi-modal information, e.g., RGB and optical flow, and thus it remains a challenge to design a better method that considers the cross-modal inputs under the cross-domain adaptation setting. To this end, we propose a unified framework for video domain adaptation, which simultaneously regularizes cross-modal and cross-domain feature representations. Specifically, we treat each modality in a domain as a view and leverage the contrastive learning technique with properly designed sampling strategies. As a result, our objectives regularize feature spaces, which originally lack the connection across modalities or have less alignment across domains. We conduct experiments on domain adaptive action recognition benchmark datasets, i.e., UCF, HMDB, and EPIC-Kitchens, and demonstrate the effectiveness of our components against state-of-the-art algorithms.

arXiv commentAccepted in ICCV'21

References in corpus (8)

• Two-Stream Convolutional Networks for Action Recognition in Videos
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• Learning Transferable Features with Deep Adaptation Networks
• Unsupervised Learning of Video Representations using LSTMs
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• Self-supervised Co-training for Video Representation Learning
• Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
• Learning Representations from Audio-Visual Spatial Alignment