Timezone: »

 
Pixel-level Correspondence for Self-Supervised Learning from Video
Yash Sharma · Yi Zhu · Chris Russell · Thomas Brox
Event URL: https://openreview.net/forum?id=ZOHvR1niqoP »

While self-supervised learning has enabled effective representation learning in the absence of labels, for vision, video remains a relatively untapped source of supervision. To address this, we propose Pixel-level Correspondence (PiCo), a method for dense contrastive learning from video. By tracking points with optical flow, we obtain a correspondence map which can be used to match local features at different points in time. We validate PiCo on standard benchmarks, outperforming self-supervised baselines on multiple dense prediction tasks, without compromising performance on image classification.

Author Information

Yash Sharma (University of Tübingen)
Yi Zhu (Amazon)
Chris Russell (Amazon)
Thomas Brox (University of Freiburg)

More from the Same Authors