← Search

Sajjad Shahabodini

2 accepted papers

2026

The Missing Point in Vision Transformers for Universal Image Segmentation

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

Cited by 0SourcecodeScholar
2025

Self-Prompting Polyp Segmentation in Colonoscopy Using Hybrid YOLO-SAM2 Model

ICASSP 2025accepted

Early diagnosis and treatment of polyps during colonoscopy are essential for reducing the incidence and mortality of Colorectal Cancer (CRC). However, the variability in polyp characteristics and the presence of artifacts in colonoscopy images and videos pose significant challenges for accurate and…

Cited by 0SourceScholar