Segment objects by expanding high-quality regions with CorrMatch
Segment objects by expanding high-quality regions with CorrMatch
CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation
arXiv paper abstract https://arxiv.org/abs/2306.04300
arXiv PDF paper https://arxiv.org/pdf/2306.04300.pdf
... present a simple but performant semi-supervised semantic segmentation approach, termed CorrMatch.
... goal is to mine more high-quality regions from the unlabeled images to leverage the unlabeled data more efficiently via consistency regularization.
... introduce an adaptive threshold updating strategy with a relaxed initialization to expand the high-quality regions.
... propose to propagate high-confidence predictions through measuring the pairwise similarities between pixels.
... show that CorrMatch achieves great performance on popular semi-supervised semantic segmentation benchmarks.
... also achieve a consistent improvement over previous semi-supervised semantic segmentation models ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
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
Comments