Segment objects with limited labels by collaboration of output and representation spaces with CSS
Segment objects with limited labels by collaboration of output and representation spaces with CSS
Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentation
arXiv paper abstract https://arxiv.org/abs/2307.09755
arXiv PDF paper https://arxiv.org/pdf/2307.09755.pdf
Semi-Supervised Semantic Segmentation (S4) aims to train a segmentation model with limited labeled images and a substantial volume of unlabeled images.
To improve the robustness of representations, powerful methods introduce a pixel-wise contrastive learning approach in latent space (i.e., representation space) that aggregates the representations to their prototypes in a fully supervised manner.
However, previous contrastive-based S4 methods merely rely on the supervision from the model’s output (logits) in logit space during unlabeled training.
In contrast, … utilize the outputs in both logit space and representation space to obtain supervision in a collaborative way.
The supervision from two spaces plays two roles: 1) reduces the risk of over-fitting to incorrect semantic information in logits with the help of representations; 2) enhances the knowledge exchange between the two spaces.
… demonstrate the competitive performance of … method compared with state-of-the-art methods.
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
