Contextual Affinity Distillation for Image Anomaly Detection

2023-07-06 · Jie Zhang, Masanori Suganuma, Takayuki Okatani

Previous works on unsupervised industrial anomaly detection mainly focus on local structural anomalies such as cracks and color contamination. While achieving significantly high detection performance on this kind of anomaly, they are faced with logical anomalies that violate the long-range dependencies such as a normal object placed in the wrong position. In this paper, based on previous knowledge distillation works, we propose to use two students (local and global) to better mimic the teacher's behavior. The local student, which is used in previous studies mainly focuses on structural anomaly detection while the global student pays attention to logical anomalies. To further encourage the global student's learning to capture long-range dependencies, we design the global context condensing block (GCCB) and propose a contextual affinity loss for the student training and anomaly scoring. Experimental results show the proposed method doesn't need cumbersome training techniques and achieves a new state-of-the-art performance on the MVTec LOCO AD dataset.

📄 PDF Abstract BibTeX arXiv:2307.03101

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly Detection Knowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Focus 설명 없음

GCTAM: Global and Contextual Truncated Affinity Combined Maximization Model For Unsupervised Graph Anomaly Detection

2026-03-02 · Xiong Zhang, Hong Peng, Zhenli He, Cheng Xie 외 arxiv

Anomalies often occur in real-world information networks/graphs, such as malevolent users, malicious comments, banned users, and fake news in social graphs. The latest graph anomaly detection methods use a novel mechanis…

Graph Anomaly Detection

Structural Teacher-Student Normality Learning for Multi-Class Anomaly Detection and Localization

2024-02-27 · Hanqiu Deng, Xingyu Li

Visual anomaly detection is a challenging open-set task aimed at identifying unknown anomalous patterns while modeling normal data. The knowledge distillation paradigm has shown remarkable performance in one-class anomal…

Anomaly Detection Knowledge Distillation Multi-class Anomaly Detection

Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection

2023-05-29 · NeurIPS 2023 11 · Hezhe Qiao, Guansong Pang

We reveal a one-class homophily phenomenon, which is one prevalent property we find empirically in real-world graph anomaly detection (GAD) datasets, i.e., normal nodes tend to have strong connection/affinity with each o…

Anomaly Detection Graph Anomaly Detection

Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection

2024-08-07 · Xinyue Liu, Jianyuan Wang, Biao Leng, Shuo Zhang

Knowledge distillation based on student-teacher network is one of the mainstream solution paradigms for the challenging unsupervised Anomaly Detection task, utilizing the difference in representation capabilities of the …

Anomaly Detection Anomaly Localization Knowledge Distillation Unsupervised Anomaly Detection

PDD: Manifold-Prior Diverse Distillation for Medical Anomaly Detection

2026-03-07 · Xijun Lu, Hongying Liu, Fanhua Shang, Yanming Hui 외 arxiv

Medical image anomaly detection faces unique challenges due to subtle, heterogeneous anomalies embedded in complex anatomical structures. Through systematic Grad-CAM analysis, we reveal that discriminative activation map…

Anomaly Detection