An Image Clustering Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids and MMD Distance

TL;DR

This paper introduces ICAE, an image clustering auto-encoder that uses predefined class centroids and MMD distance to improve clustering accuracy and interpretability, validated on multiple datasets.

Contribution

The novel ICAE algorithm combines PEDCC, data augmentation, and MMD distance within an end-to-end auto-encoder framework for enhanced image clustering.

Findings

Achieved state-of-the-art clustering results on MNIST, Fashion-MNIST, COIL20.

Effectively generates class-specific samples using predefined PEDCC centers.

Demonstrated improved generalization with Sobel smooth and reconstruction constraints.

Abstract

In this paper, we propose a novel, effective and simpler end-to-end image clustering auto-encoder algorithm: ICAE. The algorithm uses PEDCC (Predefined Evenly-Distributed Class Centroids) as the clustering centers, which ensures the inter-class distance of latent features is maximal, and adds data distribution constraint, data augmentation constraint, auto-encoder reconstruction constraint and Sobel smooth constraint to improve the clustering performance. Specifically, we perform one-to-one data augmentation to learn the more effective features. The data and the augmented data are simultaneously input into the autoencoder to obtain latent features and the augmented latent features whose similarity are constrained by an augmentation loss. Then, making use of the maximum mean discrepancy distance (MMD), we combine the latent features and augmented latent features to make their distribution close to the PEDCC distribution (uniform distribution between classes, Dirac distribution within the class) to further learn clustering-oriented features. At the same time, the MSE of the original input image and reconstructed image is used as reconstruction constraint, and the Sobel smooth loss to build generalization constraint to improve the generalization ability. Finally, extensive experiments on three common datasets MNIST, Fashion-MNIST, COIL20 are conducted. The experimental results show that the algorithm has achieved the best clustering results so far. In addition, we can use the predefined PEDCC class centers, and the decoder to clearly generate the samples of each class. The code can be downloaded at https://github.com/zyWang-Power/Clustering!