paper-with-me

홈 › Papers

Towards Training-free Anomaly Detection with Vision and Language Foundation Models

2025-03-24 · CVPR 2025 1 · Jinjin Zhang, Guodong Wang, Yizhou Jin, Di Huang

Anomaly detection is valuable for real-world applications, such as industrial quality inspection. However, most approaches focus on detecting local structural anomalies while neglecting compositional anomalies incorporating logical constraints. In this paper, we introduce LogSAD, a novel multi-modal framework that requires no training for both Logical and Structural Anomaly Detection. First, we propose a match-of-thought architecture that employs advanced large multi-modal models (i.e. GPT-4V) to generate matching proposals, formulating interests and compositional rules of thought for anomaly detection. Second, we elaborate on multi-granularity anomaly detection, consisting of patch tokens, sets of interests, and composition matching with vision and language foundation models. Subsequently, we present a calibration module to align anomaly scores from different detectors, followed by integration strategies for the final decision. Consequently, our approach addresses both logical and structural anomaly detection within a unified framework and achieves state-of-the-art results without the need for training, even when compared to supervised approaches, highlighting its robustness and effectiveness. Code is available at https://github.com/zhang0jhon/LogSAD.

📄 PDF Abstract BibTeX arXiv:2503.18325

Code (1)

zhang0jhon/logsad 공식 구현 pytorch

Tasks

Anomaly Detection

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Focus 설명 없음

Similar Papers 제목 키워드 기반

Training-Free Zero-Shot Anomaly Detection in 3D Brain MRI with 2D Foundation Models

2026-02-17 · Tai Le-Gia, Jaehyun Ahn arxiv

Zero-shot anomaly detection (ZSAD) has gained increasing attention in medical imaging as a way to identify abnormalities without task-specific supervision, but most advances remain limited to 2D datasets. Extending ZSAD …

Anomaly Detection

CoReVAD: A Contextual Reasoning Framework for Training-Free Video Anomaly Detection

2026-05-22 · Hyeongmuk Lim, Youngbum Hur arxiv

Existing Video Anomaly Detection (VAD) methods typically rely on task-specific training, leading to strong domain dependency and high training costs. Moreover, most existing methods output only scalar anomaly scores, pro…

Video Anomaly Detection

AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly Detection

2026-05-28 · Yi Zhang, Jiawen Zhu, Lele Fu, Guansong Pang arxiv

Benefiting from generalizability of vision-language models (VLMs) such as CLIP, many zero-/few-shot anomaly detection (AD) approaches have achieved impressive detection performance across various datasets. Nevertheless, …

Anomaly Detection

Human-Free Automated Prompting for Vision-Language Anomaly Detection: Prompt Optimization with Meta-guiding Prompt Scheme

2024-06-26 · Pi-Wei Chen, Jerry Chun-Wei Lin, Jia Ji, Feng-Hao Yeh 외

Pre-trained vision-language models (VLMs) are highly adaptable to various downstream tasks through few-shot learning, making prompt-based anomaly detection a promising approach. Traditional methods depend on human-crafte…

Anomaly DetectionAnomaly SegmentationFew-Shot Learning

Harnessing Large Language Models for Training-free Video Anomaly Detection

2024-04-01 · CVPR 2024 1 · Luca Zanella, Willi Menapace, Massimiliano Mancini, Yiming Wang 외

Video anomaly detection (VAD) aims to temporally locate abnormal events in a video. Existing works mostly rely on training deep models to learn the distribution of normality with either video-level supervision, one-class…

Anomaly DetectionVideo Anomaly Detection