RDDPM: Robust Denoising Diffusion Probabilistic Model for Unsupervised Anomaly Segmentation

TL;DR

This paper introduces a robust diffusion model for unsupervised anomaly segmentation that effectively handles contaminated training data, outperforming existing methods in accuracy metrics on benchmark datasets.

Contribution

The authors develop a novel robust denoising diffusion probabilistic model that operates with contaminated data, extending diffusion models' applicability to more realistic scenarios.

Findings

Outperforms state-of-the-art diffusion models in anomaly segmentation.

Achieves up to 8.08% higher AUROC on MVTec datasets.

Achieves up to 10.37% higher AUPRC on MVTec datasets.

Abstract

Recent advancements in diffusion models have demonstrated significant success in unsupervised anomaly segmentation. For anomaly segmentation, these models are first trained on normal data; then, an anomalous image is noised to an intermediate step, and the normal image is reconstructed through backward diffusion. Unlike traditional statistical methods, diffusion models do not rely on specific assumptions about the data or target anomalies, making them versatile for use across different domains. However, diffusion models typically assume access to normal data for training, limiting their applicability in realistic settings. In this paper, we propose novel robust denoising diffusion models for scenarios where only contaminated (i.e., a mix of normal and anomalous) unlabeled data is available. By casting maximum likelihood estimation of the data as a nonlinear regression problem, we reinterpret the denoising diffusion probabilistic model through a regression lens. Using robust regression, we derive a robust version of denoising diffusion probabilistic models. Our novel framework offers flexibility in constructing various robust diffusion models. Our experiments show that our approach outperforms current state of the art diffusion models, for unsupervised anomaly segmentation when only contaminated data is available. Our method outperforms existing diffusion-based approaches, achieving up to 8.08\% higher AUROC and 10.37\% higher AUPRC on MVTec datasets. The implementation code is available at: https://github.com/mehrdadmoradi124/RDDPM