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

Qian Xu; Hang Xiong; Anpeng Wang; Sam Kwong; Cong Zhang; Runmin Cong

cs.CVSep 18, 2026

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

Authors: Qian Xu, Hang Xiong, Anpeng Wang, Sam Kwong, Cong Zhang, Runmin Cong

Organizations: Shandong University Jinan, China · Alibaba International Digital Commercial Group Beijing, China · Lingnan University Hong Kong, China

Abstract

Few-shot semantic segmentation (FSS) of strip steel surface defects (S $^3$ D) has posed significant challenges distinct from natural scenes. Unlike natural images, S $^3$ D 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 $^3$ D 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 $^3$ D 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 $^3$ D 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.

Figures & tables

Fig. 1: Visualization of comparative results of Ours with MAPTNet and VRP-SAM. From top to bottom, each row illustrates the ground truth masks of support images in green, the ground truth masks of query images in yellow, and the predictions generated by various methods in red.

Fig. 2: Overview of the proposed P 3 -SAM framework. Our method consists of two core strategies: (1) Perceptual-Optimized Encoding (POE) strategy that unifies defect representation through perceptual optimization and augments shallow features with prototype and mask guided learning, and (2) Parallel Prompt Generator (PPG) strategy that generates both semantic and spatial prompts in parallel to provide comprehensive guidance for SAM’s decoder.

Dataset	Method	Backbone	mIoU(1-shot)				FB-IoU	mIoU(5-shot)				FB-IoU
Dataset	Method	Backbone	Fold-0	Fold-1	Fold-2	MEAN	FB-IoU	Fold-0	Fold-1	Fold-2	MEAN	FB-IoU
FSSD-12	TGRNet	ResNet50	61.80	62.00	48.30	57.70	73.60	62.40	59.70	47.80	58.50	75.10
	CPANet		66.00	64.00	54.60	61.50	76.10	66.50	64.90	56.30	62.60	76.30
	SCCAN		53.70	60.70	50.90	55.10	70.70	56.90	61.10	53.40	57.10	72.20
	DCP		58.30	51.70	43.10	51.00	70.60	55.90	47.00	55.70	52.90	70.90
	MAPTNet		69.70	71.30	58.60	66.50	80.00	69.00	72.30	62.60	68.00	80.60

TABLE I: Performance Comparison of mIoU and FB-IoU on FSSD-12, Surface Defects-4i and ESDIs-SOD datasets.

Fig. 3: Qualitative effect of parallel prompts on S 3 D segmentation. From left to right: query image $I_{q}$ , feature $F_{\mathrm{base}}$ captured from SAM image encoder, semantic prompt embedding $Q_{\mathrm{sem}}$ , spatial prompt embedding $F_{\mathrm{spa}}$ , and final segmentation mask $M_{\mathrm{pre}}$ .

POE	PPG	1-shot		5-shot
POE	PPG	mIoU	FB-IoU	mIoU	FB-IoU
		71.82	82.31	71.72	82.27
✓		73.92	84.07	74.01	84.14
	✓	73.69	83.58	73.68	83.58
✓	✓	75.12	85.09	75.45	85.31

TABLE II: Ablation Study of Different Strategies on FSSD-12.

Image Segmentation

Image segmentation assigns pixels or voxels to objects and regions, supporting measurement, scene understanding, and decisions across image domains.

See all 399 papers

Few-Shot Semantic Segmentation Meets SAM3
Apr 7, 2026Yi-Jen Tsai, Yen-Yu Lin, Chien-Yao WangFew-Shot Semantic Segmentation Vision Foundation Models
National Yang Ming Chiao Tung University · Institute of Information Science, Academia Sinica, Taiwan
SPDCN: Strip-based Deformable Convolutional Network for Steel Surface Defect Segmentation
Jul 23, 2026Zhongming Liu, Bingbing Jiang, Guangxin Wan +1Image Segmentation Industrial Inspection
School of Artificial Intelligence, Jiangxi Normal University, Nanchang, 330022, China · Jiangxi Provincial Key Laboratory of Intelligent Information Processing and Affective Computing, School of Artificial Intelligence, Jiangxi Normal University, Nanchang, 330022, China
Boxes2Pixels: Learning Defect Segmentation from Noisy SAM Masks
Apr 13, 2026Camile Lendering, Erkut Akdag, Egor BondarevWeakly Supervised Image Segmentation Semantic Segmentation
AIMS Group, Department of Electrical Engineering, Eindhoven University of Technology

Apr 7, 2026J/K move · Enter open · S save

Few-Shot Semantic Segmentation Meets SAM3

Yi-Jen Tsai, Yen-Yu Lin, Chien-Yao Wang

National Yang Ming Chiao Tung University · Institute of Information Science, Academia Sinica, Taiwan

Few-Shot Semantic Segmentation Vision Foundation Models Promptable Image Segmentation

Open paper AskPDF arXiv

Few-Shot Semantic Segmentation (FSS) focuses on segmenting novel object categories from only a handful of annotated examples. Most existing approaches rely on extensive episodic training to learn transferable representations, which is both computationally demanding and sensitive to distribution shifts. In this work, we revisit FSS from the perspective of modern vision foundation models and explore the potential of Segment Anything Model 3 (SAM3) as a training-free solution. By repurposing its Promptable Concept Segmentation (PCS) capability, we adopt a simple spatial concatenation strategy that places support and query images into a shared canvas, allowing a fully frozen SAM3 to perform segmentation without any fine-tuning or architectural changes. Experiments on PASCAL-

5^i

and COCO-

20^i

show that this minimal design already achieves state-of-the-art performance, outperforming many heavily engineered methods. Beyond empirical gains, we uncover that negative prompts can be counterproductive in few-shot settings, where they often weaken target representations and lead to prediction collapse despite their intended role in suppressing distractors. These findings suggest that strong cross-image reasoning can emerge from simple spatial formulations, while also highlighting limitations in how current foundation models handle conflicting prompt signals. Code at: https://github.com/WongKinYiu/FSS-SAM3

Abstract

Image Segmentation

Explore similar work

Few-Shot Semantic Segmentation Meets SAM3

SPDCN: Strip-based Deformable Convolutional Network for Steel Surface Defect Segmentation

Boxes2Pixels: Learning Defect Segmentation from Noisy SAM Masks