Self-Evolutionary Clustering

TL;DR

Self-Evolutionary Clustering (Self-EvoC) enhances deep clustering by self-supervised classification, discriminating outliers and refining target distributions, leading to superior performance on benchmark datasets.

Contribution

Introduces a modular self-evolutionary framework that uses fuzzy scoring and self-supervised learning to improve deep clustering accuracy and robustness.

Findings

Outperforms state-of-the-art deep clustering methods

Effectively discriminates outliers and improves target distribution

Achieves superior results on three benchmark datasets

Abstract

Deep clustering outperforms conventional clustering by mutually promoting representation learning and cluster assignment. However, most existing deep clustering methods suffer from two major drawbacks. First, most cluster assignment methods are based on simple distance comparison and highly dependent on the target distribution generated by a handcrafted nonlinear mapping. These facts largely limit the possible performance that deep clustering methods can reach. Second, the clustering results can be easily guided towards wrong direction by the misassigned samples in each cluster. The existing deep clustering methods are incapable of discriminating such samples. To address these issues, a novel modular Self-Evolutionary Clustering (Self-EvoC) framework is constructed, which boosts the clustering performance by classification in a self-supervised manner. Fuzzy theory is used to score the sample membership with probability which evaluates the intermediate clustering result certainty of each sample. Based on which, the most reliable samples can be selected and augmented. The augmented data are employed to fine-tune an off-the-shelf deep network classifier with the labels from the clustering, which results in a model to generate the target distribution. The proposed framework can efficiently discriminate sample outliers and generate better target distribution with the assistance of self-supervised classifier. Extensive experiments indicate that the Self-EvoC remarkably outperforms state-of-the-art deep clustering methods on three benchmark datasets.