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

Context

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, Hugging Face Daily Papers proposes Grounding Anomaly, a novel few-shot anomaly image generation framework. Hugging Face Daily Papers's 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 Vis A datasets demonstrate that Grounding Anomaly generates high-quality anomalies and achieves state-of-the-art performance across multiple downstream tasks, including anomaly detection, segmentation, and instance-level detection.