Segment objects with only image labels using pixel and semantic context in training data with DSCNet
Segment objects with only image labels using pixel and semantic context in training data with DSCNet
Weakly-supervised Semantic Segmentation via Dual-stream Contrastive Learning of Cross-image Contextual Information
arXiv paper abstract https://arxiv.org/abs/2405.04913
arXiv PDF paper https://arxiv.org/pdf/2405.04913
Weakly supervised semantic segmentation (WSSS) aims at learning a semantic segmentation model with only image-level tags.
Despite intensive research on deep learning approaches over a decade, there is still a significant performance gap between WSSS and full semantic segmentation.
Most current WSSS methods always focus on a limited single image (pixel-wise) information while ignoring the valuable inter-image (semantic-wise) information.
... end-to-end WSSS framework called DSCNet ... two innovations: i) pixel-wise group contrast and semantic-wise graph contrast ... ii) ... dual-stream contrastive learning (DSCL) ... ... handle pixel-wise and semantic-wise context information ...
Specifically, the pixel-wise group contrast learning (PGCL) and semantic-wise graph contrast learning (SGCL) tasks form a more comprehensive solution.
Extensive experiments on PASCAL VOC and MS COCO benchmarks verify the superiority of DSCNet over SOTA approaches and baseline 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