
A novel point prompting framework (PPT) that leverages curriculum learning and object-centric images to enable effective integration of frozen CLIP and SAM models for weakly-supervised referring image segmentation.


coremsg

leveraging-point-prompting-and-curriculum-learning-for-weakly-supervised-referring-image-segmentation


Leveraging Point Prompting and Curriculum Learning for Weakly-Supervised Referring Image Segmentation


title_rewrite


By progressively incorporating target-related textual cues from the input description, the proposed Progressive Comprehension Network (PCNet) enhances visual-linguistic alignment for accurate weakly-supervised referring image segmentation.


weakly-supervised-referring-image-segmentation-via-progressive-comprehension-of-target-related-textual-cues


Weakly-Supervised Referring Image Segmentation via Progressive Comprehension of Target-Related Textual Cues
