P^3-SAM: SAM with Perceptual Parallel Prompt for Few-Shot Strip Steel Surface Defect Segmentation

arXiv:2609.21424v1 Announce Type: new Abstract: Few-shot semantic segmentation (FSS) of strip steel surface defects (S^3D) has posed significant challenges distinct from natural scenes. Unlike natural images, S^3D task exhibits unique characteristics including low local contrast, uneven illumination, and complex fine-grained texture patterns. Although recent methods based on Segment Anything Model (SAM) have shown promise in FSS on natural images by leveraging SAM's powerful pre-trained representations, these unique industrial characteristics of S^3D images lead to performance drop when directly applying SAM to industrial defect scenarios. In this paper, we propose a novel Perceptual Parallel Prompt (P^3) framework that empowers SAM, creating the P^3-SAM model to address these challenges through two core strategies. First, we develop a Perceptual-Optimized Encoding (POE) strategy that enhances local contrast and preserves critical texture details for S^3D segmentation. Second, we introduce the Parallel Prompt Generator (PPG) strategy that simultaneously generates both semantic and spatial prompts, enabling comprehensive guidance for SAM's decoder across varying images. Extensive experiments on three few-shot S^3D benchmarks demonstrate that P^3-SAM achieves state-of-the-art performance, with particularly notable improvements of 12.00% in mIoU on Surface Defects-4i dataset.

Source: arXiv cs.CV | 2026-09-21