Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Jiangning, Wang, Chengjie, Li, Xiangtai, Tian, Guanzhong, Xue, Zhucun, Liu, Yong, Pang, Guansong, Tao, Dacheng
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916208620601344
author Zhang, Jiangning
Wang, Chengjie
Li, Xiangtai
Tian, Guanzhong
Xue, Zhucun
Liu, Yong
Pang, Guansong
Tao, Dacheng
author_facet Zhang, Jiangning
Wang, Chengjie
Li, Xiangtai
Tian, Guanzhong
Xue, Zhucun
Liu, Yong
Pang, Guansong
Tao, Dacheng
contents Anomaly detection (AD) is often focused on detecting anomaly areas for industrial quality inspection and medical lesion examination. However, due to the specific scenario targets, the data scale for AD is relatively small, and evaluation metrics are still deficient compared to classic vision tasks, such as object detection and semantic segmentation. To fill these gaps, this work first constructs a large-scale and general-purpose COCO-AD dataset by extending COCO to the AD field. This enables fair evaluation and sustainable development for different methods on this challenging benchmark. Moreover, current metrics such as AU-ROC have nearly reached saturation on simple datasets, which prevents a comprehensive evaluation of different methods. Inspired by the metrics in the segmentation field, we further propose several more practical threshold-dependent AD-specific metrics, ie, m$F_1$$^{.2}_{.8}$, mAcc$^{.2}_{.8}$, mIoU$^{.2}_{.8}$, and mIoU-max. Motivated by GAN inversion's high-quality reconstruction capability, we propose a simple but more powerful InvAD framework to achieve high-quality feature reconstruction. Our method improves the effectiveness of reconstruction-based methods on popular MVTec AD, VisA, and our newly proposed COCO-AD datasets under a multi-class unsupervised setting, where only a single detection model is trained to detect anomalies from different classes. Extensive ablation experiments have demonstrated the effectiveness of each component of our InvAD. Full codes and models are available at https://github.com/zhangzjn/ader.
format Preprint
id arxiv_https___arxiv_org_abs_2404_10760
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark
Zhang, Jiangning
Wang, Chengjie
Li, Xiangtai
Tian, Guanzhong
Xue, Zhucun
Liu, Yong
Pang, Guansong
Tao, Dacheng
Computer Vision and Pattern Recognition
Anomaly detection (AD) is often focused on detecting anomaly areas for industrial quality inspection and medical lesion examination. However, due to the specific scenario targets, the data scale for AD is relatively small, and evaluation metrics are still deficient compared to classic vision tasks, such as object detection and semantic segmentation. To fill these gaps, this work first constructs a large-scale and general-purpose COCO-AD dataset by extending COCO to the AD field. This enables fair evaluation and sustainable development for different methods on this challenging benchmark. Moreover, current metrics such as AU-ROC have nearly reached saturation on simple datasets, which prevents a comprehensive evaluation of different methods. Inspired by the metrics in the segmentation field, we further propose several more practical threshold-dependent AD-specific metrics, ie, m$F_1$$^{.2}_{.8}$, mAcc$^{.2}_{.8}$, mIoU$^{.2}_{.8}$, and mIoU-max. Motivated by GAN inversion's high-quality reconstruction capability, we propose a simple but more powerful InvAD framework to achieve high-quality feature reconstruction. Our method improves the effectiveness of reconstruction-based methods on popular MVTec AD, VisA, and our newly proposed COCO-AD datasets under a multi-class unsupervised setting, where only a single detection model is trained to detect anomalies from different classes. Extensive ablation experiments have demonstrated the effectiveness of each component of our InvAD. Full codes and models are available at https://github.com/zhangzjn/ader.
title Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.10760