Self-supervised Image Clustering from Multiple Incomplete Views via Constrastive Complementary Generation

TL;DR

This paper introduces CIMIC-GAN, a novel method combining GANs and contrastive learning to improve incomplete multi-view image clustering by effectively utilizing incomplete data and capturing complementarity among modalities.

Contribution

The paper proposes a new framework that integrates GAN-based data completion with double contrastive learning for better clustering of incomplete multi-view images.

Findings

CIMIC-GAN outperforms existing methods on four datasets.

The approach effectively handles high data missing rates.

It leverages both complete and incomplete data for improved representations.

Abstract

Incomplete Multi-View Clustering aims to enhance clustering performance by using data from multiple modalities. Despite the fact that several approaches for studying this issue have been proposed, the following drawbacks still persist: 1) It's difficult to learn latent representations that account for complementarity yet consistency without using label information; 2) and thus fails to take full advantage of the hidden information in incomplete data results in suboptimal clustering performance when complete data is scarce. In this paper, we propose Contrastive Incomplete Multi-View Image Clustering with Generative Adversarial Networks (CIMIC-GAN), which uses GAN to fill in incomplete data and uses double contrastive learning to learn consistency on complete and incomplete data. More specifically, considering diversity and complementary information among multiple modalities, we incorporate autoencoding representation of complete and incomplete data into double contrastive learning to achieve learning consistency. Integrating GANs into the autoencoding process can not only take full advantage of new features of incomplete data, but also better generalize the model in the presence of high data missing rates. Experiments conducted on \textcolor{black}{four} extensively-used datasets show that CIMIC-GAN outperforms state-of-the-art incomplete multi-View clustering methods.