# Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Types

arXiv: https://arxiv.org/abs/2112.11573 · HTML: https://mlsanity.com/paper/2112.11573/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 77 references that are in the map.
- First posted on arXiv 21 Dec 2021.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [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)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization](https://mlsanity.com/paper/2011.08785/) (2020)
- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [Invariant Information Clustering for Unsupervised Image Classification and Segmentation](https://mlsanity.com/paper/1807.06653/) (2018)
- [CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances](https://mlsanity.com/paper/2007.08176/) (2020)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings](https://mlsanity.com/paper/1911.02357/) (2019)
- [SCAN: Learning to Classify Images without Labels](https://mlsanity.com/paper/2005.12320/) (2020)
- [Deep Anomaly Detection Using Geometric Transformations](https://mlsanity.com/paper/1805.10917/) (2018)
- [Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering](https://mlsanity.com/paper/1611.05148/) (2016)
- [Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2006.16067/) (2020)
- [Classification-Based Anomaly Detection for General Data](https://mlsanity.com/paper/2005.02359/) (2020)
- [Joint Unsupervised Learning of Deep Representations and Image Clusters](https://mlsanity.com/paper/1604.03628/) (2016)
- [PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2010.05903/) (2020)
- [Learning and Evaluating Representations for Deep One-class Classification](https://mlsanity.com/paper/2011.02578/) (2020)
- [Learning by Transduction](https://mlsanity.com/paper/1301.7375/) (2013)
- [Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection](https://mlsanity.com/paper/2005.14140/) (2020)
- [GATCluster: Self-Supervised Gaussian-Attention Network for Image Clustering](https://mlsanity.com/paper/2002.11863/) (2020)
- [Hierarchical Subquery Evaluation for Active Learning on a Graph](https://mlsanity.com/paper/1504.08219/) (2015)
- [Multiple Instance Learning with Bag Dissimilarities](https://mlsanity.com/paper/1309.5643/) (2013)

## Built on by (most cited first, 13 of 13)

- [Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey](https://mlsanity.com/paper/2207.10298/) (2022)
- [Component-aware anomaly detection framework for adjustable and logical industrial visual inspection](https://mlsanity.com/paper/2305.08509/) (2023)
- [UniFormaly: Towards Task-Agnostic Unified Framework for Visual Anomaly Detection](https://mlsanity.com/paper/2307.12540/) (2023)
- [AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios](https://mlsanity.com/paper/2410.14379/) (2024)
- [Blind Localization and Clustering of Anomalies in Textures](https://mlsanity.com/paper/2404.12246/) (2024)
- [Multilevel Saliency-Guided Self-Supervised Learning for Image Anomaly Detection](https://mlsanity.com/paper/2311.18332/) (2023)
- [Unraveling Anomalies in Time: Unsupervised Discovery and Isolation of Anomalous Behavior in Bio-regenerative Life Support System Telemetry](https://mlsanity.com/paper/2406.09825/) (2024)
- [Example-Based Feature Painting on Textures](https://mlsanity.com/paper/2511.01513/) (2025)
- [Self-supervised Learning for Anomaly Detection in Computational Workflows](https://mlsanity.com/paper/2310.01247/) (2023)
- [Anomaly Multi-classification in Industrial Scenarios: Transferring Few-shot Learning to a New Task](https://mlsanity.com/paper/2406.05645/) (2024)
- [Anomalous Agreement: How to find the Ideal Number of Anomaly Classes in Correlated, Multivariate Time Series Data](https://mlsanity.com/paper/2501.07172/) (2025)
- [ProtoAnomalyNCD: Prototype Learning for Multi-class Novel Anomaly Discovery in Industrial Scenarios](https://mlsanity.com/paper/2511.12938/) (2025)
- [Focus and Supplement: Dual-Enhanced Vision Transformer for Multi-Class Anomaly Classification](https://mlsanity.com/paper/2609.33353/) (2026)

## Abstract (arXiv)

We study anomaly clustering, grouping data into coherent clusters of anomaly types. This is different from anomaly detection that aims to divide anomalies from normal data. Unlike object-centered image clustering, anomaly clustering is particularly challenging as anomalous patterns are subtle and local. We present a simple yet effective clustering framework using a patch-based pretrained deep embeddings and off-the-shelf clustering methods. We define a distance function between images, each of which is represented as a bag of embeddings, by the Euclidean distance between weighted averaged embeddings. The weight defines the importance of instances (i.e., patch embeddings) in the bag, which may highlight defective regions. We compute weights in an unsupervised way or in a semi-supervised way when labeled normal data is available. Extensive experimental studies show the effectiveness of the proposed clustering framework along with a novel distance function upon exist-ing multiple instance or deep clustering frameworks. Over-all, our framework achieves 0.451 and 0.674 normalized mutual information scores on MVTec object and texture categories and further improve with a few labeled normal data (0.577, 0.669), far exceeding the baselines (0.244, 0.273) or state-of-the-art deep clustering methods (0.176, 0.277).