Training Free Zero-Shot Visual Anomaly Localization via Diffusion Inversion

TL;DR

This paper presents a training-free, vision-only zero-shot anomaly localization method using diffusion model inversion, achieving state-of-the-art results without requiring fine-grained prompts or additional modalities.

Contribution

It introduces a novel diffusion inversion technique for zero-shot anomaly detection that does not rely on training or auxiliary prompts, improving spatial localization accuracy.

Findings

Achieves state-of-the-art performance on VISA dataset.

Provides effective anomaly localization without auxiliary modalities.

Operates without training, simplifying deployment.

Abstract

Zero-Shot image Anomaly Detection (ZSAD) aims to detect and localise anomalies without access to any normal training samples of the target data. While recent ZSAD approaches leverage additional modalities such as language to generate fine-grained prompts for localisation, vision-only methods remain limited to image-level classification, lacking spatial precision. In this work, we introduce a simple yet effective training-free vision-only ZSAD framework that circumvents the need for fine-grained prompts by leveraging the inversion of a pretrained Denoising Diffusion Implicit Model (DDIM). Specifically, given an input image and a generic text description (e.g., "an image of an [object class]"), we invert the image to obtain latent representations and initiate the denoising process from a fixed intermediate timestep to reconstruct the image. Since the underlying diffusion model is trained solely on normal data, this process yields a normal-looking reconstruction. The discrepancy between the input image and the reconstructed one highlights potential anomalies. Our method achieves state-of-the-art performance on VISA dataset, demonstrating strong localisation capabilities without auxiliary modalities and facilitating a shift away from prompt dependence for zero-shot anomaly detection research. Code is available at https://github.com/giddyyupp/DIVAD.