# Unsupervised Anomaly Segmentation using Image-Semantic Cycle Translation

arXiv: https://arxiv.org/abs/2103.09094 · HTML: https://mlsanity.com/paper/2103.09094/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 21 references that are in the map.
- First posted on arXiv 16 Mar 2021.

## Builds on (most cited first, 12 of 12)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study](https://mlsanity.com/paper/2004.03271/) (2020)
- [Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images](https://mlsanity.com/paper/1804.04488/) (2018)
- [Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders](https://mlsanity.com/paper/1806.04972/) (2018)
- [Unsupervised Anomaly Localization using Variational Auto-Encoders](https://mlsanity.com/paper/1907.02796/) (2019)
- [Unsupervised Lesion Detection via Image Restoration with a Normative Prior](https://mlsanity.com/paper/2005.00031/) (2020)
- [Context-encoding Variational Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1812.05941/) (2018)
- [Scale-Space Autoencoders for Unsupervised Anomaly Segmentation in Brain MRI](https://mlsanity.com/paper/2006.12852/) (2020)
- [Unsupervised Region-based Anomaly Detection in Brain MRI with Adversarial Image Inpainting](https://mlsanity.com/paper/2010.01942/) (2020)

## Built on by (most cited first, 11 of 11)

- [U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation](https://mlsanity.com/paper/2406.02918/) (2024)
- [Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images](https://mlsanity.com/paper/2403.12570/) (2024)
- [Endora: Video Generation Models as Endoscopy Simulators](https://mlsanity.com/paper/2403.11050/) (2024)
- [LGS: A Light-weight 4D Gaussian Splatting for Efficient Surgical Scene Reconstruction](https://mlsanity.com/paper/2406.16073/) (2024)
- [EndoSparse: Real-Time Sparse View Synthesis of Endoscopic Scenes using Gaussian Splatting](https://mlsanity.com/paper/2407.01029/) (2024)
- [GaussianStego: A Generalizable Stenography Pipeline for Generative 3D Gaussians Splatting](https://mlsanity.com/paper/2407.01301/) (2024)
- [Track Any Anomalous Object: A Granular Video Anomaly Detection Pipeline](https://mlsanity.com/paper/2506.05175/) (2025)
- [GTP-4o: Modality-prompted Heterogeneous Graph Learning for Omni-modal Biomedical Representation](https://mlsanity.com/paper/2407.05540/) (2024)
- [Unsupervised Anomaly Detection with Local-Sensitive VQVAE and Global-Sensitive Transformers](https://mlsanity.com/paper/2303.17505/) (2023)
- [KM-UNet KAN Mamba UNet for medical image segmentation](https://mlsanity.com/paper/2501.02559/) (2025)
- [Novel Methods for Catheter and Guidewire Segmentation in X-ray Fluoroscopy under a Federated Learning Setting](https://mlsanity.com/paper/2609.06876/) (2026)

## Abstract (arXiv)

The goal of unsupervised anomaly segmentation (UAS) is to detect the pixel-level anomalies unseen during training. It is a promising field in the medical imaging community, e.g, we can use the model trained with only healthy data to segment the lesions of rare diseases. Existing methods are mainly based on Information Bottleneck, whose underlying principle is modeling the distribution of normal anatomy via learning to compress and recover the healthy data with a low-dimensional manifold, and then detecting lesions as the outlier from this learned distribution. However, this dimensionality reduction inevitably damages the localization information, which is especially essential for pixel-level anomaly detection. In this paper, to alleviate this issue, we introduce the semantic space of healthy anatomy in the process of modeling healthy-data distribution. More precisely, we view the couple of segmentation and synthesis as a special Autoencoder, and propose a novel cycle translation framework with a journey of 'image->semantic->image'. Experimental results on the BraTS and ISLES databases show that the proposed approach achieves significantly superior performance compared to several prior methods and segments the anomalies more accurately.