A contrastive learning framework designed at a regional level to assist learning in semantic segmentation.
ReCo is a pixel-level contrastive framework — a new loss function which helps semantic segmentation not only to learn from local context (neighbouring pixels), but also from global context across the entire dataset (semantic class relationships). ReCo can perform supervised or semi-supervised contrastive learning on a pixel-level dense representation. For each semantic class in a training mini-batch, ReCo samples a set of pixel-level representations (queries), and encourages them to be close to the class mean averaged across all representations in this class (positive keys), and simultaneously pushes them away from representations sampled from other classes (negative keys).
Shikun Liu, Shuaifeng Zhi, Edward Johns and Andrew J. Davison. Bootstrapping Semantic Segmentation with Regional Contrast. arXiv2021
The ReCo software is available through the link on the right and is free to be used for non-commercial purposes. Full terms and conditions which govern its use are detailed here.