Self-supervised Video Transformer
This work addresses the need for efficient self-supervised learning in video analysis, offering a novel approach that eliminates dependency on negative samples, which is incremental but impactful for researchers in computer vision.
The paper tackles the problem of training video transformers without labeled data by proposing a self-supervised method that matches features from different spatiotemporal views of the same video, achieving strong performance on action recognition benchmarks like Kinetics-400 and converging faster with small batch sizes.
In this paper, we propose self-supervised training for video transformers using unlabeled video data. From a given video, we create local and global spatiotemporal views with varying spatial sizes and frame rates. Our self-supervised objective seeks to match the features of these different views representing the same video, to be invariant to spatiotemporal variations in actions. To the best of our knowledge, the proposed approach is the first to alleviate the dependency on negative samples or dedicated memory banks in Self-supervised Video Transformer (SVT). Further, owing to the flexibility of Transformer models, SVT supports slow-fast video processing within a single architecture using dynamically adjusted positional encoding and supports long-term relationship modeling along spatiotemporal dimensions. Our approach performs well on four action recognition benchmarks (Kinetics-400, UCF-101, HMDB-51, and SSv2) and converges faster with small batch sizes. Code: https://git.io/J1juJ