MRAD: Zero-shot Anomaly Detection With Memory-driven Retrieval
2026 · Chaoran Xu, Chengkan Lv, Qiyu Chen, et al.
Abstract
Zero-shot anomaly detection (ZSAD) often leverages pretrained vision or vision-language models, but many existing methods use prompt learning or complex modeling to fit the data distribution, resulting in high training or inference cost and limited cross-domain stability. To address these limitations, we propose Memory-Retrieval Anomaly Detection method (MRAD), a unified framework that replaces parametric fitting with a direct memory retrieval. The train-free base model, MRAD-TF, freezes the CLIP image encoder and constructs a two-level memory bank (image-level and pixel-level) from auxiliary data, where feature-label pairs are explicitly stored as keys and values. During inference, anomaly scores are obtained directly by similarity retrieval over the memory bank. Based on the MRAD-TF, we further propose two lightweight variants as enhancements: (i) MRAD-FT fine-tunes the retrieval metric with two linear layers to enhance the discriminability between normal and anomaly; (ii) MRAD-CLIP
Authors
(none)
Tags
Stats
Related papers
- Multimodal Reasoning Agent For Zero-shot Composed Image Retrieval (2025)0.00
- RAD: Retrieval-augmented Monocular Metric Depth Estimation For Underrepresented Classes (2026)0.00
- RAVID: Retrieval-augmented Visual Detection: A Knowledge-driven Approach For Ai-generated Image Identification (2025)0.00
- CLAIR: Clip-aided Weakly Supervised Zero-shot Cross-domain Image Retrieval (2025)0.00
- Hybrid-attention Based Decoupled Metric Learning For Zero-shot Image Retrieval (2019)12.93
- An Efficient Framework For Zero-shot Sketch-based Image Retrieval (2021)13.65
- Data-efficient Generalization For Zero-shot Composed Image Retrieval (2025)2.26
- Target Before Shooting: Accurate Anomaly Detection And Localization Under One Millisecond Via Cascade Patch Retrieval (2023)14.62