Segment object in an image according to a text description
Segment object in an image according to a text description
CRIS: CLIP-Driven Referring Image Segmentation
arXiv paper abstract https://arxiv.org/abs/2111.15174
arXiv PDF paper https://arxiv.org/pdf/2111.15174.pdf
Referring image segmentation aims to segment a referent via a natural linguistic expression.
… propose an end-to-end CLIP-Driven Referring Image Segmentation framework (CRIS).
… CRIS resorts to vision-language decoding and contrastive learning for achieving the text-to-pixel alignment.
… design a vision-language decoder to propagate fine-grained semantic information from textual representations to each pixel-level activation
… present text-to-pixel contrastive learning to explicitly enforce the text feature similar to the related pixel-level features and dissimilar to the irrelevances.
… demonstrate that our proposed framework significantly outperforms the state-of-the-art performance without any post-processing. …
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
