# What is Wrong with One-Class Anomaly Detection?

arXiv: https://arxiv.org/abs/2104.09793 · HTML: https://mlsanity.com/paper/2104.09793/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 20 Apr 2021.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [Multi-task Self-Supervised Visual Learning](https://mlsanity.com/paper/1708.07860/) (2017)
- [Learning De-biased Representations with Biased Representations](https://mlsanity.com/paper/1910.02806/) (2019)
- [Representation Learning by Learning to Count](https://mlsanity.com/paper/1708.06734/) (2017)
- [One-Class Convolutional Neural Network](https://mlsanity.com/paper/1901.08688/) (2019)
- [Robust, Deep and Inductive Anomaly Detection](https://mlsanity.com/paper/1704.06743/) (2017)

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

- [Building One-class Detector for Anything: Open-vocabulary Zero-shot OOD Detection Using Text-image Models](https://mlsanity.com/paper/2305.17207/) (2023)
- [Conditioning Latent-Space Clusters for Real-World Anomaly Classification](https://mlsanity.com/paper/2309.09676/) (2023)

## Abstract (arXiv)

From a safety perspective, a machine learning method embedded in real-world applications is required to distinguish irregular situations. For this reason, there has been a growing interest in the anomaly detection (AD) task. Since we cannot observe abnormal samples for most of the cases, recent AD methods attempt to formulate it as a task of classifying whether the sample is normal or not. However, they potentially fail when the given normal samples are inherited from diverse semantic labels. To tackle this problem, we introduce a latent class-condition-based AD scenario. In addition, we propose a confidence-based self-labeling AD framework tailored to our proposed scenario. Since our method leverages the hidden class information, it successfully avoids generating the undesirable loose decision region that one-class methods suffer. Our proposed framework outperforms the recent one-class AD methods in the latent multi-class scenarios.