GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sträter, Luc P. J., Salehi, Mohammadreza, Gavves, Efstratios, Snoek, Cees G. M., Asano, Yuki M.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910531175055360
author Sträter, Luc P. J.
Salehi, Mohammadreza
Gavves, Efstratios
Snoek, Cees G. M.
Asano, Yuki M.
author_facet Sträter, Luc P. J.
Salehi, Mohammadreza
Gavves, Efstratios
Snoek, Cees G. M.
Asano, Yuki M.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_12427
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features
Sträter, Luc P. J.
Salehi, Mohammadreza
Gavves, Efstratios
Snoek, Cees G. M.
Asano, Yuki M.
Computer Vision and Pattern Recognition
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.
title GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.12427