paper-with-me

홈 › Papers

LogiCo: A Unified Framework for Logical and Structural Anomaly Detection

2026-06-27 · Ximiao Zhang, Min Xu, Xiuzhuang Zhou arxiv

Current anomaly detection methods primarily focus on structural anomalies, while paying insufficient attention to anomalies that violate logical constraints. Conversely, top-performing logical anomaly detection approaches address this by modeling global semantic consistency, but perform poorly on subtle structural anomalies due to inadequate detection granularity. In this paper, we propose LogiCo, a unified framework for Logical and structural anomaly detection via Component-level feature reconstruction. Unlike existing methods that rely on explicit global semantic modeling, LogiCo employs a novel component-level feature reconstruction technique to capture inter-component logical constraints. Specifically, LogiCo maps pre-trained image features into a discrete component-level feature space and performs collaborative feature reconstruction at both component and patch levels, enabling it to effectively detect both logical and structural anomalies. Furthermore, to address the specific challenge of count-related logical anomalies, we integrate a segmentation-map discriminator that extends the model's capability to identify quantitative inconsistencies. LogiCo achieves state-of-the-art performance on both logical and structural anomaly detection across four benchmarks, including MVTec-LOCO, MVTec-AD, VisA, and Real-IAD, demonstrating its superiority and practical feasibility. The code is available at https://github.com/cnulab/LogiCo.

📄 PDF Abstract BibTeX arXiv:2606.28688

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly Detection

Similar Papers 제목 키워드 기반

LogiCode: an LLM-Driven Framework for Logical Anomaly Detection

2024-06-07 · Yiheng Zhang, Yunkang Cao, Xiaohao Xu, Weiming Shen

This paper presents LogiCode, a novel framework that leverages Large Language Models (LLMs) for identifying logical anomalies in industrial settings, moving beyond traditional focus on structural inconsistencies. By harn…

Anomaly DetectionBinary ClassificationCode GenerationLogical Reasoning+1

LogiCoL: Logically-Informed Contrastive Learning for Set-based Dense Retrieval

2025-05-26 · Yanzhen Shen, Sihao Chen, Xueqiang Xu, Yunyi Zhang 외

While significant progress has been made with dual- and bi-encoder dense retrievers, they often struggle on queries with logical connectives, a use case that is often overlooked yet important in downstream applications. …

Contrastive LearningEntity RetrievalRetrieval

TMUAD: Enhancing Logical Capabilities in Unified Anomaly Detection Models with a Text Memory Bank

2025-08-29 · Jiawei Liu, Jiahe Hou, Wei Wang, Jinsong Du 외 arxiv

Anomaly detection, which aims to identify anomalies deviating from normal patterns, is challenging due to the limited amount of normal data available. Unlike most existing unified methods that rely on carefully designed …

Anomaly Detection

UniSLAD: A Unified Framework for Structural and Logical Industrial Visual Anomaly Detection

2026-06-18 · Changyi Li, Chao Yang, Yu Xiao, Kari Tammi arxiv

Visual anomaly detection is a fundamental task in industrial automation. While existing approaches have achieved notable progress in identifying structural defects, the detection of logical anomalies remains relatively u…

Anomaly Detection

LogiCoT: Logical Chain-of-Thought Instruction-Tuning

2023-05-20 · Hanmeng Liu, Zhiyang Teng, Leyang Cui, Chaoli Zhang 외

Generative Pre-trained Transformer 4 (GPT-4) demonstrates impressive chain-of-thought reasoning ability. Recent work on self-instruction tuning, such as Alpaca, has focused on enhancing the general proficiency of models.…

Logical ReasoningText Generation