One-Step Diffusion with Inverse Residual Fields for Unsupervised Industrial Anomaly Detection

2026-04-20

AI Summary

This work addresses the slow inference speed of diffusion models in unsupervised industrial anomaly detection by proposing OSD-IRF, a novel method that trains an unconditional diffusion model and, for the first time, reveals the pronounced separability of anomalies in the Inverse Residual Field (IRF) space. Leveraging this insight, OSD-IRF constructs a highly efficient detection mechanism requiring only a single diffusion step. By integrating DDPM, IRF prediction, Gaussian density estimation, and threshold-based decision making, the method achieves state-of-the-art or competitive performance across three major benchmarks, excelling in six evaluation metrics. Notably, OSD-IRF accelerates inference by approximately 2× compared to existing approaches while eliminating the need for knowledge distillation.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Diffusion Models for Vision
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Diffusion models have achieved outstanding performance in unsupervised industrial anomaly detection (uIAD) by learning a manifold of normal data under the common assumption that off-manifold anomalies are harder to generate, resulting in larger reconstruction errors in data space or lower probability densities in the tractable latent space. However, their iterative denoising and noising nature leads to slow inference. In this paper, we propose OSD-IRF, a novel one-step diffusion with inverse residual fields, to address this limitation for uIAD task. We first train a deep diffusion probabilistic model (DDPM) on normal data without any conditioning. Then, for a test sample, we predict its inverse residual fields (IRF) based on the noise estimated by the well-trained parametric noise function of the DDPM. Finally, uIAD is performed by evaluating the probability density of the IRF under a Gaussian distribution and comparing it with a threshold. Our key observation is that anomalies become distinguishable in this IRF space, a finding that has seldom been reported in prior works. Moreover, OSD-IRF requires only single step diffusion for uIAD, thanks to the property that IRF holds for any neighboring time step in the denoising process. Extensive experiments on three widely used uIAD benchmarks show that our model achieves SOTA or competitive performance across six metrics, along with roughly a 2X inference speedup without distillation.

Problem

• unsupervised industrial anomaly detection
• diffusion models
• inference speed
• anomaly detection
• one-step diffusion

Innovation

• One-Step Diffusion
• Inverse Residual Fields
• Unsupervised Anomaly Detection
• Diffusion Models
• Industrial Inspection