Spectral Analysis Network for Deep Representation Learning and Image Clustering

by   Jinghua Wang, et al.

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.


page 4

page 5


SA-Net: A deep spectral analysis network for image clustering

Although supervised deep representation learning has attracted enormous ...

NECA: Network-Embedded Deep Representation Learning for Categorical Data

We propose NECA, a deep representation learning method for categorical d...

Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelation

Clustering is one of the most fundamental tasks in machine learning. Rec...

Supervision and Source Domain Impact on Representation Learning: A Histopathology Case Study

As many algorithms depend on a suitable representation of data, learning...

Representation Learning for Clustering via Building Consensus

In this paper, we focus on deep clustering and unsupervised representati...

Going Deeper with Spectral Embeddings

To make sense of millions of raw data and represent them efficiently, pr...

Generative Reasoning Integrated Label Noise Robust Deep Image Representation Learning in Remote Sensing

The development of deep learning based image representation learning (IR...

Please sign up or login with your details

Forgot password? Click here to reset