# Deep Image Clustering with Category-Style Representation

arXiv: https://arxiv.org/abs/2007.10004 · HTML: https://mlsanity.com/paper/2007.10004/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2020.

## Built on by (most cited first, 10 of 10)

- [PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering](https://mlsanity.com/paper/2103.17070/) (2021)
- [Preservational Learning Improves Self-supervised Medical Image Models by Reconstructing Diverse Contexts](https://mlsanity.com/paper/2109.04379/) (2021)
- [You Never Cluster Alone](https://mlsanity.com/paper/2106.01908/) (2021)
- [DivClust: Controlling Diversity in Deep Clustering](https://mlsanity.com/paper/2304.01042/) (2023)
- [Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization](https://mlsanity.com/paper/2103.04813/) (2021)
- [Deep Clustering by Semantic Contrastive Learning](https://mlsanity.com/paper/2103.02662/) (2021)
- [Information Maximization Clustering via Multi-View Self-Labelling](https://mlsanity.com/paper/2103.07368/) (2021)
- [Motif Mining: Finding and Summarizing Remixed Image Content](https://mlsanity.com/paper/2203.08327/) (2022)
- [Top-Down Deep Clustering with Multi-generator GANs](https://mlsanity.com/paper/2112.03398/) (2021)
- [Decorrelating Adversarial Nets for Clustering Mobile Network Data](https://mlsanity.com/paper/2103.08348/) (2021)

## Abstract (arXiv)

Deep clustering which adopts deep neural networks to obtain optimal representations for clustering has been widely studied recently. In this paper, we propose a novel deep image clustering framework to learn a category-style latent representation in which the category information is disentangled from image style and can be directly used as the cluster assignment. To achieve this goal, mutual information maximization is applied to embed relevant information in the latent representation. Moreover, augmentation-invariant loss is employed to disentangle the representation into category part and style part. Last but not least, a prior distribution is imposed on the latent representation to ensure the elements of the category vector can be used as the probabilities over clusters. Comprehensive experiments demonstrate that the proposed approach outperforms state-of-the-art methods significantly on five public datasets.