Image Clustering using an Augmented Generative Adversarial Network and Information Maximization

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.

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Learning deep representations by mutual information estimation and maximization
• Improved Training of Wasserstein GANs
• Energy-based Generative Adversarial Network
• Adversarial Feature Learning
• Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
• Deep Clustering for Unsupervised Learning of Visual Features
• Learning Discrete Representations via Information Maximizing Self-Augmented Training
• Unsupervised Learning by Predicting Noise
• Least Squares Generative Adversarial Networks
• Formal Limitations on the Measurement of Mutual Information
• Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

Cited by in corpus (2)

• Information Maximization Clustering via Multi-View Self-Labelling
• A Generic Self-Supervised Framework of Learning Invariant Discriminative Features