Bootstrapping Semantic Segmentation with Regional Contrast

04/09/2021 ∙ by Shikun Liu, et al. ∙ 7

We present ReCo, a contrastive learning framework designed at a regional level to assist learning in semantic segmentation. ReCo performs semi-supervised or supervised 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 in both semi-supervised and supervised semantic segmentation methods, achieving smoother segmentation boundaries and faster convergence. The strongest effect is in semi-supervised learning with very few labels. With ReCo, we achieve 50 whilst requiring only 20 labelled images, improving by 10 previous state-of-the-art. Code is available at



There are no comments yet.


page 2

page 6

page 10

page 11

page 14

page 20

page 21

page 22

Code Repositories


The implementation of "Bootstrapping Semantic Segmentation with Regional Contrast".

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.