Spectral Analysis Network for Deep Representation Learning and Image Clustering

TL;DR

This paper introduces a novel unsupervised deep learning network based on spectral analysis that improves image clustering by capturing local similarities, deep correlations, and integrating multiple spectral techniques.

Contribution

It proposes a new spectral analysis-based network structure for unsupervised deep representation learning, enhancing robustness and clustering performance.

Findings

Effective in various image clustering tasks

Robust against occlusion due to local similarity detection

Capable of revealing deep data correlations

Abstract

Deep representation learning is a crucial procedure in multimedia analysis and attracts increasing attention. Most of the popular techniques rely on convolutional neural network and require a large amount of labeled data in the training procedure. However, it is time consuming or even impossible to obtain the label information in some tasks due to cost limitation. Thus, it is necessary to develop unsupervised deep representation learning techniques. This paper proposes a new network structure for unsupervised deep representation learning based on spectral analysis, which is a popular technique with solid theory foundations. Compared with the existing spectral analysis methods, the proposed network structure has at least three advantages. Firstly, it can identify the local similarities among images in patch level and thus more robust against occlusion. Secondly, through multiple consecutive spectral analysis procedures, the proposed network can learn more clustering-friendly representations and is capable to reveal the deep correlations among data samples. Thirdly, it can elegantly integrate different spectral analysis procedures, so that each spectral analysis procedure can have their individual strengths in dealing with different data sample distributions. Extensive experimental results show the effectiveness of the proposed methods on various image clustering tasks.