# Confidence-Aware and Self-Supervised Image Anomaly Localisation

arXiv: https://arxiv.org/abs/2303.13227 · HTML: https://mlsanity.com/paper/2303.13227/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 23 Mar 2023.

## Builds on (most cited first, 20 of 20)

- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Data-Efficient Image Recognition with Contrastive Predictive Coding](https://mlsanity.com/paper/1905.09272/) (2019)
- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1906.12340/) (2019)
- [GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training](https://mlsanity.com/paper/1805.06725/) (2018)
- [Diffusion Models for Medical Anomaly Detection](https://mlsanity.com/paper/2203.04306/) (2022)
- [PHiSeg: Capturing Uncertainty in Medical Image Segmentation](https://mlsanity.com/paper/1906.04045/) (2019)
- [Efficient GAN-Based Anomaly Detection](https://mlsanity.com/paper/1802.06222/) (2018)
- [Is Out-of-Distribution Detection Learnable?](https://mlsanity.com/paper/2210.14707/) (2022)
- [Detecting Outliers with Foreign Patch Interpolation](https://mlsanity.com/paper/2011.04197/) (2020)
- [Detecting Outliers with Poisson Image Interpolation](https://mlsanity.com/paper/2107.02622/) (2021)
- [Anomaly Detection in Medical Imaging -- A Mini Review](https://mlsanity.com/paper/2108.11986/) (2021)
- [Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT](https://mlsanity.com/paper/1905.12806/) (2019)
- [A Benchmark of Medical Out of Distribution Detection](https://mlsanity.com/paper/2007.04250/) (2020)
- [Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-based CT Image Augmentation for Object Detection](https://mlsanity.com/paper/1906.04962/) (2019)
- [Deep Generative Models in the Real-World: An Open Challenge from Medical Imaging](https://mlsanity.com/paper/1806.05452/) (2018)
- [Self-Supervised Out-of-Distribution Detection in Brain CT Scans](https://mlsanity.com/paper/2011.05428/) (2020)
- [Unsupervised anomaly localization using VAE and beta-VAE](https://mlsanity.com/paper/2005.10686/) (2020)
- [Out-of-Distribution Detection for Skin Lesion Images with Deep Isolation Forest](https://mlsanity.com/paper/2003.09365/) (2020)
- [CVAD: A generic medical anomaly detector based on Cascade VAE](https://mlsanity.com/paper/2110.15811/) (2021)

## Built on by (most cited first, 4 of 4)

- [MedIAnomaly: A comparative study of anomaly detection in medical images](https://mlsanity.com/paper/2404.04518/) (2024)
- [Enhancing Reconstruction-Based Out-of-Distribution Detection in Brain MRI with Model and Metric Ensembles](https://mlsanity.com/paper/2412.17586/) (2024)
- [Differentiable Score-Based Likelihoods: Learning CT Motion Compensation From Clean Images](https://mlsanity.com/paper/2404.14747/) (2024)
- [Unsupervised Anomaly Detection of Diseases in the Female Pelvis for Real-Time MR Imaging](https://mlsanity.com/paper/2602.06179/) (2026)

## Abstract (arXiv)

Universal anomaly detection still remains a challenging problem in machine learning and medical image analysis. It is possible to learn an expected distribution from a single class of normative samples, e.g., through epistemic uncertainty estimates, auto-encoding models, or from synthetic anomalies in a self-supervised way. The performance of self-supervised anomaly detection approaches is still inferior compared to methods that use examples from known unknown classes to shape the decision boundary. However, outlier exposure methods often do not identify unknown unknowns. Here we discuss an improved self-supervised single-class training strategy that supports the approximation of probabilistic inference with loosen feature locality constraints. We show that up-scaling of gradients with histogram-equalised images is beneficial for recently proposed self-supervision tasks. Our method is integrated into several out-of-distribution (OOD) detection models and we show evidence that our method outperforms the state-of-the-art on various benchmark datasets.