cs.CVNov 9, 2026

TIRAD: Text-guided Image Residual Learning for Generalist Anomaly Detection

Authors: Seongsu Lee, Seunghyun Oh, Seungjae Moon, Youngmin Ro

Organizations: Machine Intelligence Laboratory, Dept. of Artificial Intelligence, University of Seoul, Korea

Abstract

Recent anomaly detection studies have shown that residual features, which model the discrepancy between normal and abnormal patterns, provide strong generalization to anomalies unseen during training. However, existing residual-based approaches mainly rely on visual discrepancies derived from image representations, while semantic discrepancies that can be explicitly expressed through language remain largely underexplored. To address this problem, we propose TIRAD, Text-guided Image Residual Learning for Generalist Anomaly Detection, a multimodal residual learning framework that defines the discrepancy between textual representations of normal and abnormal states as a Text Residual Feature and uses it to guide the Image Residual Feature. Specifically, a Text Fusion Module converts patch-level text residuals into a gate that modulates the image residual of each patch. The gate retains the visual discrepancies that the text residual identifies as defect-related and attenuates the others, leading to more discriminative anomaly representations. Extensive experiments on industrial benchmarks and industrial-to-medical transfer demonstrate that the proposed method outperforms existing image-centric residual learning methods.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. A Structured Benchmark for Text-Guided Anomaly Detection: When Language Stops Conditioning the Decision

    Jun 1, 2026Stefano Samele, Eugenio Lomurno, Teodora Jovanovic +3VLM EvaluationIndustrial Anomaly Detection

  2. DART: Domain-Agnostic Residual Transfer for Generalist Anomaly Detection

    Nov 5, 2026Muhammad Aqeel, Maham Nazir, Marco Cristani +1Anomaly DetectionDomain Generalization

  3. Res2^2CLIP: Few-Shot Generalist Anomaly Detection with Residual-to-Residual Alignment

    May 15, 2026Xinyue Liu, Jianyuan Wang, Biao Leng +1Few-Shot Anomaly DetectionVLM Adaptation