홈 › Papers

FB-CLIP: Fine-Grained Zero-Shot Anomaly Detection with Foreground-Background Disentanglement

2026-03-20 · Ming Hu, Yongsheng Huo, Mingyu Dou, Jianfu Yin, Peng Zhao, Yao Wang, Cong Hu, Bingliang Hu, Quan Wang arxiv

Fine-grained anomaly detection is crucial in industrial and medical applications, but labeled anomalies are often scarce, making zero-shot detection challenging. While vision-language models like CLIP offer promising solutions, they struggle with foreground-background feature entanglement and coarse textual semantics. We propose FB-CLIP, a framework that enhances anomaly localization via multi-strategy textual representations and foreground-background separation. In the textual modality, it combines End-of-Text features, global-pooled representations, and attention-weighted token features for richer semantic cues. In the visual modality, multi-view soft separation along identity, semantic, and spatial dimensions, together with background suppression, reduces interference and improves discriminability. Semantic Consistency Regularization (SCR) aligns image features with normal and abnormal textual prototypes, suppressing uncertain matches and enlarging semantic gaps. Experiments show that FB-CLIP effectively distinguishes anomalies from complex backgrounds, achieving accurate fine-grained anomaly detection and localization under zero-shot settings.

📄 PDF Abstract BibTeX arXiv:2603.19608

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly Detection

Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization

2023-08-30 · Hanqiu Deng, Zhaoxiang Zhang, Jinan Bao, Xingyu Li

Contrastive Language-Image Pre-training (CLIP) models have shown promising performance on zero-shot visual recognition tasks by learning visual representations under natural language supervision. Recent studies attempt t…

Anomaly Detection Anomaly Localization Test-time Adaptation zero-shot anomaly detection

Bridge Feature Matching and Cross-Modal Alignment with Mutual-filtering for Zero-shot Anomaly Detection

2025-07-15 · Yuhu Bai, Jiangning Zhang, Yunkang Cao, Guangyuan Lu 외

With the advent of vision-language models (e.g., CLIP) in zero- and few-shot settings, CLIP has been widely applied to zero-shot anomaly detection (ZSAD) in recent research, where the rare classes are essential and expec…

Anomaly Classification Anomaly Detection cross-modal alignment zero-shot anomaly detection

Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detections

2025-04-15 · Alireza Salehi, Mohammadreza Salehi, Reshad Hosseini, Cees G. M. Snoek 외

Anomaly Detection (AD) involves identifying deviations from normal data distributions and is critical in fields such as medical diagnostics and industrial defect detection. Traditional AD methods typically require the av…

Anomaly Detection Anomaly Localization Defect Detection Prompt Learning+2

KAnoCLIP: Zero-Shot Anomaly Detection through Knowledge-Driven Prompt Learning and Enhanced Cross-Modal Integration

2025-01-07 · Chengyuan Li, Suyang Zhou, Jieping Kong, Lei Qi 외

Zero-shot anomaly detection (ZSAD) identifies anomalies without needing training samples from the target dataset, essential for scenarios with privacy concerns or limited data. Vision-language models like CLIP show poten…

Anomaly Detection Anomaly Segmentation General Knowledge Large Language Model+4

SSVP: Synergistic Semantic-Visual Prompting for Industrial Zero-Shot Anomaly Detection

2026-01-14 · Chenhao Fu, Han Fang, Xiuzheng Zheng, Wenbo Wei 외 arxiv

Zero-Shot Anomaly Detection (ZSAD) leverages Vision-Language Models (VLMs) to enable supervision-free industrial inspection. However, existing ZSAD paradigms are constrained by single visual backbones, which struggle to …