GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesis

TL;DR

GroundingAnomaly is a novel few-shot anomaly synthesis framework that uses spatial conditioning and gated self-attention to generate high-quality anomalies, improving industrial quality control tasks.

Contribution

It introduces a spatial conditioning module and gated self-attention for precise anomaly synthesis, addressing limitations of prior inpainting-based methods.

Findings

Achieves state-of-the-art results on MVTec AD and VisA datasets.

Generates high-quality anomalies for various downstream tasks.

Enhances anomaly detection, segmentation, and instance detection performance.

Abstract

The performance of visual anomaly inspection in industrial quality control is often constrained by the scarcity of real anomalous samples. Consequently, anomaly synthesis techniques have been developed to enlarge training sets and enhance downstream inspection. However, existing methods either suffer from poor integration caused by inpainting or fail to provide accurate masks. To address these limitations, we propose GroundingAnomaly, a novel few-shot anomaly image generation framework. Our framework introduces a Spatial Conditioning Module that leverages per-pixel semantic maps to enable precise spatial control over the synthesized anomalies. Furthermore, a Gated Self-Attention Module is designed to inject conditioning tokens into a frozen U-Net via gated attention layers. This carefully preserves pretrained priors while ensuring stable few-shot adaptation. Extensive evaluations on the MVTec AD and VisA datasets demonstrate that GroundingAnomaly generates high-quality anomalies and achieves state-of-the-art performance across multiple downstream tasks, including anomaly detection, segmentation, and instance-level detection.