Dual Adversarial Auto-Encoders for Clustering

Abstract

As a powerful approach for exploratory data analysis, unsupervised clustering is a fundamental task in computer vision and pattern recognition. Many clustering algorithms have been developed, but most of them perform unsatisfactorily on the data with complex structures. Recently, Adversarial Auto-Encoder (AAE) shows effectiveness on tackling such data by combining Auto-Encoder (AE) and adversarial training, but it cannot effectively extract classification information from the unlabeled data. In this work, we propose Dual Adversarial Auto-encoder (Dual-AAE) which simultaneously maximizes the likelihood function and mutual information between observed examples and a subset of latent variables. By performing variational inference on the objective function of Dual-AAE, we derive a new reconstruction loss which can be optimized by training a pair of Auto-encoders. Moreover, to avoid mode collapse, we introduce the clustering regularization term for the category variable. Experiments on four benchmarks show that Dual-AAE achieves superior performance over state-of-the-art clustering methods. Besides, by adding a reject option, the clustering accuracy of Dual-AAE can reach that of supervised CNN algorithms. Dual-AAE can also be used for disentangling style and content of images without using supervised information.

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Auto-Encoding Variational Bayes
• Wasserstein GAN
• Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
• Unrolled Generative Adversarial Networks
• Improving Variational Inference with Inverse Autoregressive Flow
• EM Algorithms for Weighted-Data Clustering with Application to Audio-Visual Scene Analysis
• Improving Variational Auto-Encoders using Householder Flow

Cited by in corpus (8)

• Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain
• Unsupervised Domain Adaptation via Discriminative Manifold Propagation
• Learning Target Domain Specific Classifier for Partial Domain Adaptation
• Decoding Structure-Spectrum Relationships with Physically Organized Latent Spaces
• Multiple Flat Projections for Cross-manifold Clustering
• Graph Polish: A Novel Graph Generation Paradigm for Molecular Optimization
• FMNet: Latent Feature-wise Mapping Network for Cleaning up Noisy Micro-Doppler Spectrogram
• Multi-local Collaborative AutoEncoder