Deep Image Clustering with Category-Style Representation

by   Junjie Zhao, et al.

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.


Graph Contrastive Clustering

Recently, some contrastive learning methods have been proposed to simult...

Deep Spectral Clustering using Dual Autoencoder Network

The clustering methods have recently absorbed even-increasing attention ...

Deep Comprehensive Correlation Mining for Image Clustering

Recent developed deep unsupervised methods allow us to jointly learn rep...

Forced to Learn: Discovering Disentangled Representations Without Exhaustive Labels

Learning a better representation with neural networks is a challenging p...

Domestic Activity Clustering from Audio via Depthwise Separable Convolutional Autoencoder Network

Automatic estimation of domestic activities from audio can be used to so...

Preserving Domain Private Representation via Mutual Information Maximization

Recent advances in unsupervised domain adaptation have shown that mitiga...

VoronoiNet: General Functional Approximators with Local Support

Voronoi diagrams are highly compact representations that are used in var...

Code Repositories


Official PyTorch implementation for ECCV'20 paper: Deep Image Clustering with Category-Style Representation

view repo