Few-Shot Anomaly Detection via Category-Agnostic Registration Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909341448142848 |
|---|---|
| author | Huang, Chaoqin Guan, Haoyan Jiang, Aofan Zhang, Ya Spratling, Michael Wang, Xinchao Wang, Yanfeng |
| author_facet | Huang, Chaoqin Guan, Haoyan Jiang, Aofan Zhang, Ya Spratling, Michael Wang, Xinchao Wang, Yanfeng |
| contents | Most existing anomaly detection (AD) methods require a dedicated model for each category. Such a paradigm, despite its promising results, is computationally expensive and inefficient, thereby failing to meet the requirements for realworld applications. Inspired by how humans detect anomalies, by comparing a query image to known normal ones, this article proposes a novel few-shot AD (FSAD) framework. Using a training set of normal images from various categories, registration, aiming to align normal images of the same categories, is leveraged as the proxy task for self-supervised category-agnostic representation learning. At test time, an image and its corresponding support set, consisting of a few normal images from the same category, are supplied, and anomalies are identified by comparing the registered features of the test image to its corresponding support image features. Such a setup enables the model to generalize to novel test categories. It is, to our best knowledge, the first FSAD method that requires no model fine-tuning for novel categories: enabling a single model to be applied to all categories. Extensive experiments demonstrate the effectiveness of the proposed method. Particularly, it improves the current state-of-the-art (SOTA) for FSAD by 11.3% and 8.3% on the MVTec and MPDD benchmarks, respectively. The source code is available at https://github.com/Haoyan-Guan/CAReg. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_08810 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Few-Shot Anomaly Detection via Category-Agnostic Registration Learning Huang, Chaoqin Guan, Haoyan Jiang, Aofan Zhang, Ya Spratling, Michael Wang, Xinchao Wang, Yanfeng Computer Vision and Pattern Recognition Most existing anomaly detection (AD) methods require a dedicated model for each category. Such a paradigm, despite its promising results, is computationally expensive and inefficient, thereby failing to meet the requirements for realworld applications. Inspired by how humans detect anomalies, by comparing a query image to known normal ones, this article proposes a novel few-shot AD (FSAD) framework. Using a training set of normal images from various categories, registration, aiming to align normal images of the same categories, is leveraged as the proxy task for self-supervised category-agnostic representation learning. At test time, an image and its corresponding support set, consisting of a few normal images from the same category, are supplied, and anomalies are identified by comparing the registered features of the test image to its corresponding support image features. Such a setup enables the model to generalize to novel test categories. It is, to our best knowledge, the first FSAD method that requires no model fine-tuning for novel categories: enabling a single model to be applied to all categories. Extensive experiments demonstrate the effectiveness of the proposed method. Particularly, it improves the current state-of-the-art (SOTA) for FSAD by 11.3% and 8.3% on the MVTec and MPDD benchmarks, respectively. The source code is available at https://github.com/Haoyan-Guan/CAReg. |
| title | Few-Shot Anomaly Detection via Category-Agnostic Registration Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.08810 |