# Semantic Iterative Reconstruction: One-Shot Universal Anomaly Detection

arXiv: https://arxiv.org/abs/2603.23766 · HTML: https://mlsanity.com/paper/2603.23766/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Builds on (most cited first, 25 of 25)

- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification](https://mlsanity.com/paper/2107.02314/) (2021)
- [Anomaly Detection via Reverse Distillation from One-Class Embedding](https://mlsanity.com/paper/2201.10703/) (2022)
- [GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training](https://mlsanity.com/paper/1805.06725/) (2018)
- [Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders](https://mlsanity.com/paper/1807.02011/) (2018)
- [VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations](https://mlsanity.com/paper/2012.15029/) (2020)
- [AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models](https://mlsanity.com/paper/2308.15366/) (2023)
- [Student-Teacher Feature Pyramid Matching for Anomaly Detection](https://mlsanity.com/paper/2103.04257/) (2021)
- [Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection](https://mlsanity.com/paper/2405.14325/) (2024)
- [Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts](https://mlsanity.com/paper/2403.06495/) (2024)
- [Attention Based Glaucoma Detection: A Large-scale Database and CNN Model](https://mlsanity.com/paper/1903.10831/) (2019)
- [Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images](https://mlsanity.com/paper/2403.12570/) (2024)
- [ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction](https://mlsanity.com/paper/2306.02602/) (2023)
- [AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2](https://mlsanity.com/paper/2405.14529/) (2024)
- [Mask, Stitch, and Re-Sample: Enhancing Robustness and Generalizability in Anomaly Detection through Automatic Diffusion Models](https://mlsanity.com/paper/2305.19643/) (2023)
- [Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection](https://mlsanity.com/paper/2503.02424/) (2025)
- [Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation](https://mlsanity.com/paper/2408.13509/) (2024)
- [ADTR: Anomaly Detection Transformer with Feature Reconstruction](https://mlsanity.com/paper/2209.01816/) (2022)
- [Unsupervised Anomaly Localization with Structural Feature-Autoencoders](https://mlsanity.com/paper/2208.10992/) (2022)
- [A Survey on Diffusion Models for Anomaly Detection](https://mlsanity.com/paper/2501.11430/) (2025)
- [Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detection](https://mlsanity.com/paper/2503.19357/) (2025)
- [PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomalies](https://mlsanity.com/paper/2506.09237/) (2025)
- [One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection](https://mlsanity.com/paper/2502.01201/) (2025)
- [Dual Distillation for Few-Shot Anomaly Detection](https://mlsanity.com/paper/2603.01713/) (2026)

## Abstract (arXiv)

Unsupervised medical anomaly detection is severely limited by the scarcity of normal training samples. Existing methods typically train dedicated models for each dataset or disease, requiring hundreds of normal images per task and lacking cross-modality generalization. We propose Semantic Iterative Reconstruction (SIR), a framework that enables a single universal model to detect anomalies across diverse medical domains using extremely few normal samples. SIR leverages a pretrained teacher encoder to extract multi-scale deep features and employs a compact up-then-down decoder with multi-loop iterative refinement to enforce robust normality priors in deep feature space. The framework adopts a one-shot universal design: a single model is trained by mixing exactly one normal sample from each of nine heterogeneous datasets, enabling effective anomaly detection on all corresponding test sets without task-specific retraining. Extensive experiments on nine medical benchmarks demonstrate that SIR achieves state-of-the-art under all four settings -- one-shot universal, full-shot universal, one-shot specialized, and full-shot specialized -- consistently outperforming previous methods. SIR offers an efficient and scalable solution for multi-domain clinical anomaly detection.