GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features
This work addresses the challenge of cross-domain anomaly detection, which is crucial for applications like self-driving cars and industrial inspection, by providing a unified framework that performs well across different anomaly types with minimal adjustments.
The paper tackled the problem of anomaly detection across diverse domains, such as semantic and industrial anomalies, by proposing GeneralAD, a framework that uses Vision Transformers and a self-supervised anomaly generation module, achieving state-of-the-art results on six out of ten datasets and competitive performance on the others for both detection and localization tasks.
In the domain of anomaly detection, methods often excel in either high-level semantic or low-level industrial benchmarks, rarely achieving cross-domain proficiency. Semantic anomalies are novelties that differ in meaning from the training set, like unseen objects in self-driving cars. In contrast, industrial anomalies are subtle defects that preserve semantic meaning, such as cracks in airplane components. In this paper, we present GeneralAD, an anomaly detection framework designed to operate in semantic, near-distribution, and industrial settings with minimal per-task adjustments. In our approach, we capitalize on the inherent design of Vision Transformers, which are trained on image patches, thereby ensuring that the last hidden states retain a patch-based structure. We propose a novel self-supervised anomaly generation module that employs straightforward operations like noise addition and shuffling to patch features to construct pseudo-abnormal samples. These features are fed to an attention-based discriminator, which is trained to score every patch in the image. With this, our method can both accurately identify anomalies at the image level and also generate interpretable anomaly maps. We extensively evaluated our approach on ten datasets, achieving state-of-the-art results in six and on-par performance in the remaining for both localization and detection tasks.