CVAug 23, 2020

Dual Adversarial Auto-Encoders for Clustering

arXiv:2008.10038v151 citations
Originality Highly original
AI Analysis

This addresses the challenge of extracting classification information from unlabeled data for clustering in computer vision and pattern recognition, representing a novel method for a known bottleneck.

The paper tackled the problem of unsupervised clustering on data with complex structures by proposing Dual Adversarial Auto-Encoder (Dual-AAE), which achieved superior performance over state-of-the-art methods on four benchmarks and matched supervised CNN accuracy with a reject option.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes