4 papers
Information Router for Mitigating Modality Dominance in Vision-Language Models
Seulgi Kim, Mohit Prabhushankar, Ghassan AlRegib
Vision Language models (VLMs) have demonstrated strong performance across a wide range of benchmarks, yet they often suffer from modality dominance, where predictions rely dispropo…
BALD-SAM: Disagreement-based Active Prompting in Interactive Segmentation
Prithwijit Chowdhury, Mohit Prabhushankar, Ghassan AlRegib
The Segment Anything Model (SAM) has revolutionized interactive segmentation through spatial prompting. While existing work primarily focuses on automating prompts in various setti…
Countering Multi-modal Representation Collapse through Rank-targeted Fusion
Seulgi Kim, Kiran Kokilepersaud, Mohit Prabhushankar +1
Multi-modal fusion methods often suffer from two types of representation collapse: feature collapse where individual dimensions lose their discriminative power (as measured by eige…
Scale-Aware Self-Supervised Learning for Segmentation of Small and Sparse Structures
Jorge Quesada, Ghassan AlRegib
Self-supervised learning (SSL) has emerged as a powerful strategy for representation learning under limited annotation regimes, yet its effectiveness remains highly sensitive to ma…