Saved in:
Bibliographic Details
Main Authors: Jin, Xiao, Diao, Liang, Xiao, Qixin, Hu, Yifan, Zhang, Ziqi, Liu, Yuchen, Gu, Haisong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.21459
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912789060124672
author Jin, Xiao
Diao, Liang
Xiao, Qixin
Hu, Yifan
Zhang, Ziqi
Liu, Yuchen
Gu, Haisong
author_facet Jin, Xiao
Diao, Liang
Xiao, Qixin
Hu, Yifan
Zhang, Ziqi
Liu, Yuchen
Gu, Haisong
contents Anomaly detection holds considerable industrial significance, especially in scenarios with limited anomalous data. Currently, reconstruction-based and unsupervised representation-based approaches are the primary focus. However, unsupervised representation-based methods struggle to extract robust features under domain shift, whereas reconstruction-based methods often suffer from low training efficiency and performance degradation due to insufficient constraints. To address these challenges, we propose a novel method named Compressed Global Feature Conditioned Anomaly Detection (CCAD). CCAD synergizes the strengths of both paradigms by adapting global features as a new modality condition for the reconstruction model. Furthermore, we design an adaptive compression mechanism to enhance both generalization and training efficiency. Extensive experiments demonstrate that CCAD consistently outperforms state-of-the-art methods in terms of AUC while achieving faster convergence. In addition, we contribute a reorganized and re-annotated version of the DAGM 2007 dataset with new annotations to further validate our method's effectiveness. The code for reproducing main results is available at https://github.com/chloeqxq/CCAD.
format Preprint
id arxiv_https___arxiv_org_abs_2512_21459
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CCAD: Compressed Global Feature Conditioned Anomaly Detection
Jin, Xiao
Diao, Liang
Xiao, Qixin
Hu, Yifan
Zhang, Ziqi
Liu, Yuchen
Gu, Haisong
Computer Vision and Pattern Recognition
Machine Learning
Anomaly detection holds considerable industrial significance, especially in scenarios with limited anomalous data. Currently, reconstruction-based and unsupervised representation-based approaches are the primary focus. However, unsupervised representation-based methods struggle to extract robust features under domain shift, whereas reconstruction-based methods often suffer from low training efficiency and performance degradation due to insufficient constraints. To address these challenges, we propose a novel method named Compressed Global Feature Conditioned Anomaly Detection (CCAD). CCAD synergizes the strengths of both paradigms by adapting global features as a new modality condition for the reconstruction model. Furthermore, we design an adaptive compression mechanism to enhance both generalization and training efficiency. Extensive experiments demonstrate that CCAD consistently outperforms state-of-the-art methods in terms of AUC while achieving faster convergence. In addition, we contribute a reorganized and re-annotated version of the DAGM 2007 dataset with new annotations to further validate our method's effectiveness. The code for reproducing main results is available at https://github.com/chloeqxq/CCAD.
title CCAD: Compressed Global Feature Conditioned Anomaly Detection
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2512.21459