cs.CVNov 14, 2026

EviRef: Evidence-Specific Memories for Logical Anomaly Detection across Capture Conditions

Authors: Yaoting Huang, Wenqi Cai, Yijin Wei, Jianjian Qin, Chunzhi Gu, Haoran Xie, Chao Zhang

Organizations: University of Toyama · NingboTech University · University of Fukui · Japan Advanced Institute of Science and Technology

Abstract

Logical anomalies arise when every component looks normal but their combination violates the scene rules. In practical inspection, these rules must hold under varying backgrounds, illumination, and imaging quality, with only a few dozen normal images per scene, whereas existing methods couple normality with appearance and merge different constraints into one reference. We model logical normality as decomposable constraints and propose EviRef, a training-free method that builds a separate reference memory for each family of evidence. Component prototypes built once per scene parse images under any capture condition into one label space, on which occupancy and relation constraints are verified. Semantic constraints are verified with whole-image embeddings independent of parsing, and additional evidence such as text is admitted through a task-level gate without modifying existing memories. On VID-AD, EviRef attains a mean image-level area under the receiver operating characteristic curve (AUROC) of 92.1% (88.9% with visual evidence alone), the highest among the compared methods under each of five capture conditions, with a standard deviation of 0.5. Even with memories built from only 20 normal images per task, it surpasses all compared methods that use 50 normal images per task.

Figures & tables

Explore similar work

CardsList
  1. CASCADE: Constraint-Aware SCAffolded DEcomposition for Logical Anomaly Detection

    Nov 10, 2026Jinchan Kim, Jinhee Im, Hyunsouk ChoLogical Anomaly DetectionAnomaly Detection

  2. When Rule Violations Are Rare: Chimera Training for Logical Anomaly Detection

    May 25, 2026Alejandro Ascarate, Leo Lebrat, Rodrigo Santa Cruz +2Logical Anomaly DetectionCounterfactual Data Augmentation

  3. Robust Logical Anomaly Detection under Capture Shifts via Synthetic Anomalies

    Oct 13, 2026Ufuk Efe, Alptekin TemizelLogical Anomaly DetectionAnomaly Detection