2026
The Missing Point in Vision Transformers for Universal Image Segmentation
Sajjad Shahabodini, Mobina Mansoori, Farnoush Bayatmakou, Jamshid Abouei, Konstantinos Plataniotis, Arash Mohammadi
CVPR 2026
Image segmentation remains a challenging task in computer vision, demanding robust mask generation and precise classification. Recent mask-based approaches yield high-quality masks by capturing global context. However, accurately classifying these masks, especially in the presence of ambiguous bound