Segmentation with only a few examples by using image captions instead of pixel labels with IMR-HSNet
Segmentation with only a few examples by using image captions instead of pixel labels with IMR-HSNet
Iterative Few-shot Semantic Segmentation from Image Label Text
arXiv paper abstract https://arxiv.org/abs/2303.05646
arXiv PDF paper https://arxiv.org/pdf/2303.05646.pdf
GitHub https://github.com/whileherham/imr-hsnet
Few-shot semantic segmentation aims to learn to segment unseen class objects with the guidance of only a few support images.
Most previous methods rely on the pixel-level label of support images.
In this paper … focus on a more challenging setting, in which only the image-level labels are available.
… propose a general framework to firstly generate coarse masks with the help of the powerful vision-language model CLIP, and then iteratively and mutually refine the mask predictions of support and query images.
… method not only outperforms the state-of-the-art weakly supervised approaches by a significant margin, but also achieves comparable or better results to recent supervised methods.
… method owns an excellent generalization ability for the images in the wild and uncommon classes …
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