CVJun 29

PGE-SAM: Prompt-Guided Feature Enhancement for Interactive Segmentation under Degradation

arXiv:2606.304778.9
Predicted impact top 47% in CV · last 90 daysOriginality Incremental advance
AI Analysis

Improves interactive segmentation under degradation for medical and natural imaging applications, addressing a practical bottleneck in SAM's deployment.

PGE-SAM enhances SAM's robustness to real-world image degradations (noise, blur, compression) by using user prompts and prior masks to guide feature restoration, achieving SOTA performance on medical and natural images with fewer parameters.

Segment Anything Model (SAM) has revolutionized promptable image segmentation with strong zero-shot generalization. However, its performance degrades substantially under real-world imaging artifacts such as noise, blur, and compression. Existing methods restore features globally without focusing on segmentation-relevant regions and neglect SAM's iterative refinement mechanism, leading to suboptimal performance in interactive settings. We propose Prompt-Guided Feature Enhancement SAM (PGE-SAM), a framework that explicitly leverages user prompts and prior mask predictions to spatially guide the feature restoration process toward regions of interest through a Prompt Guidance Generator. To recover fine-grained details lost under degradation, we introduce Multi-Scale Features Interaction to incorporate low-level encoder features, along with a Foreground Reconstruction Loss that restricts feature-level supervision to the segmentation target. Furthermore, we present DM-Seg, a benchmark for interactive segmentation on degraded medical images, spanning multiple imaging modalities with both general and modality-specific degradations at varying severity levels. Extensive experiments demonstrate that PGE-SAM achieves SOTA robustness on both medical and natural image domains across multiple degradation levels, while maintaining generalization to clean images and adding less than one-fifth of the parameters of prior methods.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes