登录
洞察 - Weakly-Supervised Referring Image Segmentation
Weakly-Supervised Referring Image Segmentation via Progressive Comprehension of Target-Related Textual Cues
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.
Leveraging Point Prompting and Curriculum Learning for Weakly-Supervised Referring Image Segmentation
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.
