Problem
Research questions and friction points this paper is trying to address.
Zero-Shot Image Segmentation
Low Spatial Resolution
Structural Information Loss
MARS-CLIP: Multi-Resolution and Attention Refined Zero-Shot Image Segmentation
🤖 AI Summary
为解决CLIP在零样本图像分割任务中因分辨率低和结构信息丢失导致的问题，提出MARS-CLIP框架，通过多分辨率特征提取和注意力细化机制提升分割精度。
📝 Abstract
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) an attention refinement mechanism that injects spatial and color biases from intermediate layers into the final self-attention block to accurately restore object boundaries. A set of experiments on six public datasets demonstrates that MARS-CLIP significantly outperforms state-of-the-art methods.
Innovation
Methods, ideas, or system contributions that make the work stand out.
multi-resolution feature extraction
attention refinement mechanism
zero-shot semantic segmentation
🔎 Similar Papers
No similar papers found.
