# A Single Image Is All You Need: Zero-Shot Anomaly Localization Without Training Data

arXiv: https://arxiv.org/abs/2509.18354 · HTML: https://mlsanity.com/paper/2509.18354/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Builds on (most cited first, 22 of 22)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [Implicit Regularization in Deep Matrix Factorization](https://mlsanity.com/paper/1905.13655/) (2019)
- [WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation](https://mlsanity.com/paper/2303.14814/) (2023)
- [AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2310.18961/) (2023)
- [Inpaint Anything: Segment Anything Meets Image Inpainting](https://mlsanity.com/paper/2304.06790/) (2023)
- [APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD](https://mlsanity.com/paper/2305.17382/) (2023)
- ["Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors](https://mlsanity.com/paper/1812.00467/) (2018)
- [FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization](https://mlsanity.com/paper/2404.13671/) (2024)
- [Super-Identity Convolutional Neural Network for Face Hallucination](https://mlsanity.com/paper/1811.02328/) (2018)
- [Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection](https://mlsanity.com/paper/2503.10080/) (2025)
- [DeepTensor: Low-Rank Tensor Decomposition with Deep Network Priors](https://mlsanity.com/paper/2204.03145/) (2022)
- [Real Time Fabric Defect Detection System on an Embedded DSP Platform](https://mlsanity.com/paper/1410.0371/) (2014)
- [MotionSwap](https://mlsanity.com/paper/2508.06430/) (2025)

## Abstract (arXiv)

Anomaly detection in images is typically addressed by learning from collections of training data or relying on reference samples. In many real-world scenarios, however, such training data may be unavailable, and only the test image itself is provided. We address this zero-shot setting by proposing a single-image anomaly localization method that leverages the inductive bias of convolutional neural networks, inspired by Deep Image Prior (DIP). Our method is named Single Shot Decomposition Network (SSDnet). Our key assumption is that natural images often exhibit unified textures and patterns, and that anomalies manifest as localized deviations from these repetitive or stochastic patterns. To learn the deep image prior, we design a patch-based training framework where the input image is fed directly into the network for self-reconstruction, rather than mapping random noise to the image as done in DIP. To avoid the model simply learning an identity mapping, we apply masking, patch shuffling, and small Gaussian noise. In addition, we use a perceptual loss based on inner-product similarity to capture structure beyond pixel fidelity. Our approach needs no external training data, labels, or references, and remains robust in the presence of noise or missing pixels. SSDnet achieves 0.99 AUROC and 0.60 AUPRC on MVTec-AD and 0.98 AUROC and 0.67 AUPRC on the fabric dataset, outperforming state-of-the-art methods. The implementation code will be released at https://github.com/mehrdadmoradi124/SSDnet