Vague Prototype-Oriented Diffusion Model for Multi-Class Anomaly Detection

Yuxin Li, Yaoxuan Feng, Bo Chen, Wenchao Chen, Yubiao Wang, Xinyue Hu, Baolin Sun, Chunhui Qu, Mingyuan Zhou
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:27771-27790, 2024.

Abstract

Multi-class unsupervised anomaly detection aims to create a unified model for identifying anomalies in objects from multiple classes when only normal data is available. In such a challenging setting, widely used reconstruction-based networks persistently grapple with the "identical shortcut" problem, wherein the infiltration of abnormal information from the condition biases the output towards an anomalous distribution. In response to this critical challenge, we introduce a Vague Prototype-Oriented Diffusion Model (VPDM) that extracts only fundamental information from the condition to prevent the occurrence of the "identical shortcut" problem from the input layer. This model leverages prototypes that contain only vague information about the target as the initial condition. Subsequently, a novel conditional diffusion model is introduced to incrementally enhance details based on vague conditions. Finally, a Vague Prototype-Oriented Optimal Transport (VPOT) method is proposed to provide more accurate information about conditions. All these components are seamlessly integrated into a unified optimization objective. The effectiveness of our approach is demonstrated across diverse datasets, including the MVTec, VisA, and MPDD benchmarks, achieving state-of-the-art results.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-li24u, title = {Vague Prototype-Oriented Diffusion Model for Multi-Class Anomaly Detection}, author = {Li, Yuxin and Feng, Yaoxuan and Chen, Bo and Chen, Wenchao and Wang, Yubiao and Hu, Xinyue and Sun, Baolin and Qu, Chunhui and Zhou, Mingyuan}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {27771--27790}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/li24u/li24u.pdf}, url = {https://proceedings.mlr.press/v235/li24u.html}, abstract = {Multi-class unsupervised anomaly detection aims to create a unified model for identifying anomalies in objects from multiple classes when only normal data is available. In such a challenging setting, widely used reconstruction-based networks persistently grapple with the "identical shortcut" problem, wherein the infiltration of abnormal information from the condition biases the output towards an anomalous distribution. In response to this critical challenge, we introduce a Vague Prototype-Oriented Diffusion Model (VPDM) that extracts only fundamental information from the condition to prevent the occurrence of the "identical shortcut" problem from the input layer. This model leverages prototypes that contain only vague information about the target as the initial condition. Subsequently, a novel conditional diffusion model is introduced to incrementally enhance details based on vague conditions. Finally, a Vague Prototype-Oriented Optimal Transport (VPOT) method is proposed to provide more accurate information about conditions. All these components are seamlessly integrated into a unified optimization objective. The effectiveness of our approach is demonstrated across diverse datasets, including the MVTec, VisA, and MPDD benchmarks, achieving state-of-the-art results.} }
Endnote
%0 Conference Paper %T Vague Prototype-Oriented Diffusion Model for Multi-Class Anomaly Detection %A Yuxin Li %A Yaoxuan Feng %A Bo Chen %A Wenchao Chen %A Yubiao Wang %A Xinyue Hu %A Baolin Sun %A Chunhui Qu %A Mingyuan Zhou %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-li24u %I PMLR %P 27771--27790 %U https://proceedings.mlr.press/v235/li24u.html %V 235 %X Multi-class unsupervised anomaly detection aims to create a unified model for identifying anomalies in objects from multiple classes when only normal data is available. In such a challenging setting, widely used reconstruction-based networks persistently grapple with the "identical shortcut" problem, wherein the infiltration of abnormal information from the condition biases the output towards an anomalous distribution. In response to this critical challenge, we introduce a Vague Prototype-Oriented Diffusion Model (VPDM) that extracts only fundamental information from the condition to prevent the occurrence of the "identical shortcut" problem from the input layer. This model leverages prototypes that contain only vague information about the target as the initial condition. Subsequently, a novel conditional diffusion model is introduced to incrementally enhance details based on vague conditions. Finally, a Vague Prototype-Oriented Optimal Transport (VPOT) method is proposed to provide more accurate information about conditions. All these components are seamlessly integrated into a unified optimization objective. The effectiveness of our approach is demonstrated across diverse datasets, including the MVTec, VisA, and MPDD benchmarks, achieving state-of-the-art results.
APA
Li, Y., Feng, Y., Chen, B., Chen, W., Wang, Y., Hu, X., Sun, B., Qu, C. & Zhou, M.. (2024). Vague Prototype-Oriented Diffusion Model for Multi-Class Anomaly Detection. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:27771-27790 Available from https://proceedings.mlr.press/v235/li24u.html.

Related Material