Deep Discriminative Clustering Analysis

Abstract

Traditional clustering methods often perform clustering with low-level indiscriminative representations and ignore relationships between patterns, resulting in slight achievements in the era of deep learning. To handle this problem, we develop Deep Discriminative Clustering (DDC) that models the clustering task by investigating relationships between patterns with a deep neural network. Technically, a global constraint is introduced to adaptively estimate the relationships, and a local constraint is developed to endow the network with the capability of learning high-level discriminative representations. By iteratively training the network and estimating the relationships in a mini-batch manner, DDC theoretically converges and the trained network enables to generate a group of discriminative representations that can be treated as clustering centers for straightway clustering. Extensive experiments strongly demonstrate that DDC outperforms current methods on eight image, text and audio datasets concurrently.

References in corpus (19)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Deep Residual Learning for Image Recognition
• Going Deeper with Convolutions
• Fully Convolutional Networks for Semantic Segmentation
• Rich feature hierarchies for accurate object detection and semantic segmentation
• Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
• Deep Clustering for Unsupervised Learning of Visual Features
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
• Stacked What-Where Auto-encoders
• Joint Unsupervised Learning of Deep Representations and Image Clusters
• Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering
• Kernel clustering: density biases and solutions
• Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization
• Deep Continuous Clustering
• Hierarchical Clustering with Structural Constraints
• Learning Markov Clustering Networks for Scene Text Detection
• Fast Approximate Spectral Clustering for Dynamic Networks
• Variational Wasserstein Clustering
• Dimensionality's Blessing: Clustering Images by Underlying Distribution

Cited by in corpus (9)

• SPICE: Semantic Pseudo-labeling for Image Clustering
• Twin Contrastive Learning for Online Clustering
• Deep Image Clustering with Contrastive Learning and Multi-scale Graph Convolutional Networks
• Deep Robust Clustering by Contrastive Learning
• Information Maximization Clustering via Multi-View Self-Labelling
• Doubly Contrastive Deep Clustering
• Deep Clustering by Semantic Contrastive Learning
• Cluster Analysis with Deep Embeddings and Contrastive Learning
• You Never Cluster Alone