# DINO-AD: Unsupervised Anomaly Detection with Frozen DINO-V3 Features

arXiv: https://arxiv.org/abs/2602.03870 · HTML: https://mlsanity.com/paper/2602.03870/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 10 references that are in the map.
- First posted on arXiv 31 Jan 2026.

## Builds on (most cited first, 8 of 8)

- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization](https://mlsanity.com/paper/2011.08785/) (2020)
- [DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection](https://mlsanity.com/paper/2108.07610/) (2021)
- [Anomaly Detection via Reverse Distillation from One-Class Embedding](https://mlsanity.com/paper/2201.10703/) (2022)
- [Student-Teacher Feature Pyramid Matching for Anomaly Detection](https://mlsanity.com/paper/2103.04257/) (2021)
- [BMAD: Benchmarks for Medical Anomaly Detection](https://mlsanity.com/paper/2306.11876/) (2023)
- [AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2](https://mlsanity.com/paper/2405.14529/) (2024)
- [Anomaly Detection by Clustering DINO Embeddings using a Dirichlet Process Mixture](https://mlsanity.com/paper/2509.19997/) (2025)

## Built on by (most cited first, 2 of 2)

- [Real-World On-Vehicle Evaluation of Embedding-Based Anomaly Detection](https://mlsanity.com/paper/2605.19744/) (2026)
- [HiMatch-AD: DINOv3-driven Hierarchical Matching for Training-free Medical Anomaly Detection](https://mlsanity.com/paper/2606.22556/) (2026)

## Abstract (arXiv)

Unsupervised anomaly detection (AD) in medical images aims to identify abnormal regions without relying on pixel-level annotations, which is crucial for scalable and label-efficient diagnostic systems. In this paper, we propose a novel anomaly detection framework based on DINO-V3 representations, termed DINO-AD, which leverages self-supervised visual features for precise and interpretable anomaly localization. Specifically, we introduce an embedding similarity matching strategy to select a semantically aligned support image and a foreground-aware K-means clustering module to model the distribution of normal features. Anomaly maps are then computed by comparing the query features with clustered normal embeddings through cosine similarity. Experimental results on both the Brain and Liver datasets demonstrate that our method achieves superior quantitative performance compared with state-of-the-art approaches, achieving AUROC scores of up to 98.71. Qualitative results further confirm that our framework produces clearer and more accurate anomaly localization. Extensive ablation studies validate the effectiveness of each proposed component, highlighting the robustness and generalizability of our approach.