TY - GEN
T1 - Dual Memory-Guided Probabilistic Model for Weakly-Supervised Anomaly Detection
AU - Chou, Hsiu Hua
AU - Xu, Ruyi
AU - Huang, Kang Yang
AU - Wu, Jhih Ciang
AU - Shuai, Hong Han
AU - Cheng, Wen-Huang
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025
Y1 - 2025
N2 - Anomaly detection seeks to identify the patterns of instances distinguishable from normal ones. However, current methods primarily align with either one-class or open-set scenarios, leading to an inadequate exploration of anomalous examples. In this paper, we propose a weakly-supervised approach, the Dual Memory-guided Probabilistic Model (DMPM), to explore the comprehensive knowledge of normal and abnormal instances. Employing such dual memory banks, our model provides opposing guidance for probabilistic models during the denoising procedure. We illustrate the effectiveness of our DMPM in addressing weakly-supervised anomaly detection and conduct extensive experiments on popular industrial benchmarks, i.e., MVTec AD and VisA. Moreover, we highlight the adaptability of the unified DMPM, demonstrating its compatibility with diffusion-based approaches that perform on image or latent space.
AB - Anomaly detection seeks to identify the patterns of instances distinguishable from normal ones. However, current methods primarily align with either one-class or open-set scenarios, leading to an inadequate exploration of anomalous examples. In this paper, we propose a weakly-supervised approach, the Dual Memory-guided Probabilistic Model (DMPM), to explore the comprehensive knowledge of normal and abnormal instances. Employing such dual memory banks, our model provides opposing guidance for probabilistic models during the denoising procedure. We illustrate the effectiveness of our DMPM in addressing weakly-supervised anomaly detection and conduct extensive experiments on popular industrial benchmarks, i.e., MVTec AD and VisA. Moreover, we highlight the adaptability of the unified DMPM, demonstrating its compatibility with diffusion-based approaches that perform on image or latent space.
KW - Anomaly detection
KW - Diffusion model
KW - Weakly-supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85210269179&partnerID=8YFLogxK
U2 - 10.1007/978-981-97-9003-6_4
DO - 10.1007/978-981-97-9003-6_4
M3 - Conference contribution
AN - SCOPUS:85210269179
SN - 9789819790029
T3 - Communications in Computer and Information Science
SP - 50
EP - 65
BT - Human Activity Recognition and Anomaly Detection - 4th International Workshop, DL-HAR 2024, and 1st International Workshop, ADFM 2024, Held in Conjunction with IJCAI 2024, Revised Selected Papers
A2 - Peng, Kuan-Chuan
A2 - Wang, Yizhou
A2 - Li, Ziyue
A2 - Chen, Zhenghua
A2 - Wu, Min
A2 - Yang, Jianfei
A2 - Suh, Sungho
PB - Springer Science and Business Media Deutschland GmbH
T2 - 4th International Workshop on Deep Learning for Human Activity Recognition, DL-HAR 2024, and 1st International Workshop on Anomaly Detection with Foundation Models, ADFM 2024, Held in Conjunction with the International Joint Conference on AI, IJCAI 2024
Y2 - 3 August 2024 through 9 August 2024
ER -