Self-supervised learning using video by using optical flow to track points with PiCo
Self-supervised learning using video by using optical flow to track points with PiCo
Pixel-level Correspondence for Self-Supervised Learning from Video
arXiv paper abstract https://arxiv.org/abs/2207.03866v1
arXiv PDF paper https://arxiv.org/pdf/2207.03866v1.pdf
While self-supervised learning has enabled effective representation learning in the absence of labels, for vision, video remains a relatively untapped source of supervision.
… propose Pixel-level Correspondence (PiCo), a method for dense contrastive learning from video.
By tracking points with optical flow, … obtain a correspondence map which can be used to match local features at different points in time.
… PiCo on standard benchmarks, outperforming self-supervised baselines on multiple dense prediction tasks, without compromising performance on image classification.
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
