Keywords: semi-supervised learning, semantic segmentation, contrastive learning
Abstract: We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation. ReCo performs pixel-level contrastive learning on a sparse set of hard negative pixels, with minimal additional memory footprint. ReCo is easy to implement, being built on top of off-the-shelf segmentation networks, and consistently improves performance, achieving more accurate segmentation boundaries and faster convergence. The strongest effect is in semi-supervised learning with very few labels. With ReCo, we achieve high quality semantic segmentation model, requiring only 5 examples of each semantic class.
One-sentence Summary: We present a pixel-level contrastive learning framework to achieve a high-quality semantic segmeantation model trained with very few human annotations.
Supplementary Material: zip