Weakly supervised segmentation using multi-class transformer with MCTformer+
Weakly supervised segmentation using multi-class transformer with MCTformer+
MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation
arXiv paper abstract https://arxiv.org/abs/2308.03005
arXiv PDF paper https://arxiv.org/pdf/2308.03005.pdf
This paper proposes a novel transformer-based framework that aims to enhance weakly supervised semantic segmentation (WSSS) by generating accurate class-specific object localization maps as pseudo labels.
… explore the potential of the transformer model to capture class-specific attention for class-discriminative object localization by learning multiple class tokens.
… introduce a Multi-Class Token transformer, which incorporates multiple class tokens to enable class-aware interactions with the patch tokens.
… Contrastive-Class-Token (CCT) module is proposed to enhance the learning of discriminative class tokens, enabling the model to better capture the unique characteristics and properties of each class.
As a result, class-discriminative object localization maps can be effectively generated by leveraging the class-to-patch attentions associated with different class tokens.
… resulting in significantly improved WSSS performance …
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
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
