SOURCE-LINKED INTELLIGENCE

MARS-CLIP: Multi-Resolution and Attention Refined Zero-Shot Image Segmentation

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in zero-shot transfer but often struggles with dense prediction tasks due to low spatial resolution and the loss of structural information. To address these limitations, we propose MARS-CLIP (Multi-resolution and Attention Refined Segmentation for CLIP), a novel framework for zero-shot semantic segmentation. Our approach introduces two key strategies: (i) a multi-resolution feature extraction module that fuses local fine-grained features with global context to overcome input resolution constraints, and (ii)

Read original source ↗ Open in workspace

recordType

paper

region

Global