CVJun 27

LogiCo: A Unified Framework for Logical and Structural Anomaly Detection

arXiv:2606.2868814.4Has Code
Predicted impact top 19% in CV · last 90 daysOriginality Incremental advance
AI Analysis

This work addresses the need for a single method that can handle both logical and structural anomalies in industrial inspection, which previously required separate approaches.

LogiCo proposes a unified framework for detecting both logical and structural anomalies using component-level feature reconstruction, achieving state-of-the-art performance on four benchmarks including MVTec-LOCO, MVTec-AD, VisA, and Real-IAD.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes