DeltaDeno: Zero-Shot Anomaly Generation via Delta-Denoising Attribution

2025-11-20

AI Summary

To address overfitting in zero-shot anomaly generation caused by the absence of authentic anomaly samples—rendering conventional fine-tuning ineffective—this paper proposes a novel diffusion-based paradigm that requires neither training nor access to any anomaly samples. Methodologically, we design a dual-branch contrastive denoising architecture: subtle prompt perturbations induce divergent denoising trajectories, and accumulated denoising residuals enable interpretable, pixel-level anomaly localization. We further enhance generation stability and local controllability via token-level prompt refinement, latent-space localized inpainting, and constrained spatial attention biasing. To our knowledge, this is the first approach achieving high-fidelity, explainable, *fully* zero-shot localized anomaly synthesis—without any anomaly annotations or model adaptation. Extensive experiments on multiple public benchmarks demonstrate significant improvements in downstream anomaly detection performance.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Anomaly generation is often framed as few-shot fine-tuning with anomalous samples, which contradicts the scarcity that motivates generation and tends to overfit category priors. We tackle the setting where no real anomaly samples or training are available. We propose Delta-Denoising (DeltaDeno), a training-free zero-shot anomaly generation method that localizes and edits defects by contrasting two diffusion branches driven by a minimal prompt pair under a shared schedule. By accumulating per-step denoising deltas into an image-specific localization map, we obtain a mask to guide the latent inpainting during later diffusion steps and preserve the surrounding context while generating realistic local defects. To improve stability and control, DeltaDeno performs token-level prompt refinement that aligns shared content and strengthens anomaly tokens, and applies a spatial attention bias restricted to anomaly tokens in the predicted region. Experiments on public datasets show that DeltaDeno achieves great generation, realism and consistent gains in downstream detection performance. Code will be made publicly available.

Problem

• Generating realistic anomalies without training data or real samples
• Localizing and editing defects using diffusion model contrast
• Improving anomaly detection through zero-shot generation method

Innovation

• Zero-shot anomaly generation without training
• Delta-denoising attribution for defect localization
• Token-level prompt refinement and spatial attention bias