Image Clustering using an Augmented Generative Adversarial Network and Information Maximization

TL;DR

This paper introduces a deep clustering framework combining a modified GAN with Sobel operations and an auxiliary classifier, significantly improving image clustering performance on multiple datasets by enhancing feature separability and robustness.

Contribution

The novel integration of Sobel operations into a GAN-based clustering framework and the use of an adaptive, multi-head auxiliary classifier for improved robustness and handling of imbalanced data.

Findings

Outperforms state-of-the-art methods on CIFAR-10 and CIFAR-100.

Achieves competitive results on STL10 and MNIST.

Enhances feature separability and robustness in image clustering.

Abstract

Image clustering has recently attracted significant attention due to the increased availability of unlabelled datasets. The efficiency of traditional clustering algorithms heavily depends on the distance functions used and the dimensionality of the features. Therefore, performance degradation is often observed when tackling either unprocessed images or high-dimensional features extracted from processed images. To deal with these challenges, we propose a deep clustering framework consisting of a modified generative adversarial network (GAN) and an auxiliary classifier. The modification employs Sobel operations prior to the discriminator of the GAN to enhance the separability of the learned features. The discriminator is then leveraged to generate representations as the input to an auxiliary classifier. An adaptive objective function is utilised to train the auxiliary classifier for clustering the representations, aiming to increase the robustness by minimizing the divergence of multiple representations generated by the discriminator. The auxiliary classifier is implemented with a group of multiple cluster-heads, where a tolerance hyper-parameter is used to tackle imbalanced data. Our results indicate that the proposed method significantly outperforms state-of-the-art clustering methods on CIFAR-10 and CIFAR-100, and is competitive on the STL10 and MNIST datasets.