DART improves anomaly detection across unseen and varied domains

DART: Domain-Agnostic Residual Transfer for Generalist Anomaly Detection

Computer Vision and Pattern RecognitionArtificial IntelligenceMachine Learning

Summary

Detecting unusual or faulty items in new settings is hard because the appearance can change a lot. The authors introduce DART, a method that separates what makes something truly abnormal from normal differences between settings like texture or lighting. This separation helps the system better spot problems even when it hasn’t seen those exact conditions before. They tested DART on several benchmarks and found it consistently improved existing methods, especially when the differences between conditions were bigger.

What this means in practice

  • For quality control teams: Improve defect detection in manufacturing processes where product appearance varies across different factories or equipment setups.
  • For medical imaging analysts: Enhance automated identification of abnormalities in medical scans despite differences in scanners or image acquisition conditions.

Authors

Muhammad Aqeel, Maham Nazir, Marco Cristani, Francesco Setti

Abstract

Generalist Anomaly Detection (GAD) aims to detect anomalies in unseen domains using only a few reference samples. Recent normal-abnormal guided methods improve this setting by exploiting abnormal references, but their residuals often mix transferable anomaly cues with domain-specific appearance factors such as texture, geometry, and acquisition conditions. This residual domain entanglement limits cross-domain transfer and may produce spurious activations on novel domains. We propose DART, a plug-in framework for normal-abnormal guided GAD that learns to separate residuals into anomaly-relevant and domain-specific components. DART combines a Residual Disentanglement Module, which preserves anomaly-discriminative information while suppressing domain information, with Cross-Domain Meta-Training, which forms episodes across source domains to make the separation effective. The method is architecture-agnostic and can be inserted between residual computation and the detection head of existing GAD pipelines. Experiments on MVTec AD, VisA, and BraTS show consistent improvements over multiple base methods, with the largest gains under stronger domain shifts. https://github.com/aqeeelmirza/DART