Training Free Zero-Shot Visual Anomaly Localization via Diffusion Inversion
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Anomaly DetectionSimilar Papers 제목 키워드 기반
AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly Detection
Benefiting from generalizability of vision-language models (VLMs) such as CLIP, many zero-/few-shot anomaly detection (AD) approaches have achieved impressive detection performance across various datasets. Nevertheless, …
Anomaly DetectionBootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization
Contrastive Language-Image Pre-training (CLIP) models have shown promising performance on zero-shot visual recognition tasks by learning visual representations under natural language supervision. Recent studies attempt t…
Anomaly DetectionAnomaly LocalizationTest-time Adaptationzero-shot anomaly detectionVisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformer
Zero-shot anomaly detection (ZSAD) requires detecting and localizing anomalies without access to target-class anomaly samples. Mainstream methods rely on vision-language models (VLMs) such as CLIP: they build hand-crafte…
Anomaly DetectionMetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning
Zero- and few-shot visual anomaly segmentation relies on powerful vision-language models that detect unseen anomalies using manually designed textual prompts. However, visual representations are inherently independent of…
Anomaly DetectionAnomaly SegmentationMeta-LearningSegmentation+1Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection
Large vision-language models (LVLMs) are markedly proficient in deriving visual representations guided by natural language. Recent explorations have utilized LVLMs to tackle zero-shot visual anomaly detection (VAD) chall…
Anomaly DetectionAnomaly LocalizationImage to textLanguage Modelling+2