Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelation

05/31/2021
by   Yaling Tao, et al.
0

Clustering is one of the most fundamental tasks in machine learning. Recently, deep clustering has become a major trend in clustering techniques. Representation learning often plays an important role in the effectiveness of deep clustering, and thus can be a principal cause of performance degradation. In this paper, we propose a clustering-friendly representation learning method using instance discrimination and feature decorrelation. Our deep-learning-based representation learning method is motivated by the properties of classical spectral clustering. Instance discrimination learns similarities among data and feature decorrelation removes redundant correlation among features. We utilize an instance discrimination method in which learning individual instance classes leads to learning similarity among instances. Through detailed experiments and examination, we show that the approach can be adapted to learning a latent space for clustering. We design novel softmax-formulated decorrelation constraints for learning. In evaluations of image clustering using CIFAR-10 and ImageNet-10, our method achieves accuracy of 81.5 constraints are compatible with various neural networks.

READ FULL TEXT
research
07/13/2022

Unsupervised Visual Representation Learning by Synchronous Momentum Grouping

In this paper, we propose a genuine group-level contrastive visual repre...
research
03/09/2020

Deep Inverse Feature Learning: A Representation Learning of Error

This paper introduces a novel perspective about error in machine learnin...
research
06/28/2023

Semantic Positive Pairs for Enhancing Contrastive Instance Discrimination

Self-supervised learning algorithms based on instance discrimination eff...
research
09/11/2020

Spectral Analysis Network for Deep Representation Learning and Image Clustering

Deep representation learning is a crucial procedure in multimedia analys...
research
07/11/2020

Relation-Guided Representation Learning

Deep auto-encoders (DAEs) have achieved great success in learning data r...
research
01/28/2019

Hierarchically Clustered Representation Learning

The joint optimization of representation learning and clustering in the ...
research
09/11/2020

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

Although supervised deep representation learning has attracted enormous ...

Please sign up or login with your details

Forgot password? Click here to reset