Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization

Abstract

Image clustering is one of the most important computer vision applications, which has been extensively studied in literature. However, current clustering methods mostly suffer from lack of efficiency and scalability when dealing with large-scale and high-dimensional data. In this paper, we propose a new clustering model, called DEeP Embedded RegularIzed ClusTering (DEPICT), which efficiently maps data into a discriminative embedding subspace and precisely predicts cluster assignments. DEPICT generally consists of a multinomial logistic regression function stacked on top of a multi-layer convolutional autoencoder. We define a clustering objective function using relative entropy (KL divergence) minimization, regularized by a prior for the frequency of cluster assignments. An alternating strategy is then derived to optimize the objective by updating parameters and estimating cluster assignments. Furthermore, we employ the reconstruction loss functions in our autoencoder, as a data-dependent regularization term, to prevent the deep embedding function from overfitting. In order to benefit from end-to-end optimization and eliminate the necessity for layer-wise pretraining, we introduce a joint learning framework to minimize the unified clustering and reconstruction loss functions together and train all network layers simultaneously. Experimental results indicate the superiority and faster running time of DEPICT in real-world clustering tasks, where no labeled data is available for hyper-parameter tuning.

Cited by in corpus (17)

• Clustering with Deep Learning: Taxonomy and New Methods
• SpectralNet: Spectral Clustering using Deep Neural Networks
• Deep Continuous Clustering
• Deep Discriminative Clustering Analysis
• Gaussian Mixture Generative Adversarial Networks for Diverse Datasets, and the Unsupervised Clustering of Images
• Automatically Discovering and Learning New Visual Categories with Ranking Statistics
• Learning to Discover Novel Visual Categories via Deep Transfer Clustering
• Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data
• Deep Discriminative Latent Space for Clustering
• Deep Image Clustering with Category-Style Representation
• MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation
• Trainable Activation Function in Image Classification
• Deep Transformation-Invariant Clustering
• EKO: Adaptive Sampling of Compressed Video Data
• Clustering high dimensional meteorological scenarios: results and performance index
• Deep convolutional autoencoder for cryptocurrency market analysis
• A Self-supervised Learning System for Object Detection in Videos Using Random Walks on Graphs