Improving Pixel-Level Contrastive Learning by Leveraging Exogenous Depth Information. (arXiv:2211.10177v1 [cs.CV])

Self-supervised representation learning based on Contrastive Learning (CL)
has been the subject of much attention in recent years. This is due to the
excellent results obtained on a variety of subsequent tasks (in particular
classification), without requiring a large amount of labeled samples. However,
most reference CL algorithms (such as SimCLR and MoCo, but also BYOL and Barlow
Twins) are not adapted to pixel-level downstream tasks. One existing solution
known as PixPro proposes a pixel-level approach that is based on …

arxiv exogenous information pixel