Deep Robust Clustering by Contrastive Learning

08/07/2020
by   Huasong Zhong, et al.
0

Recently, many unsupervised deep learning methods have been proposed to learn clustering with unlabelled data. By introducing data augmentation, most of the latest methods look into deep clustering from the perspective that the original image and its tansformation should share similar semantic clustering assignment. However, the representation features before softmax activation function could be quite different even the assignment probability is very similar since softmax is only sensitive to the maximum value. This may result in high intra-class diversities in the representation feature space, which will lead to unstable local optimal and thus harm the clustering performance. By investigating the internal relationship between mutual information and contrastive learning, we summarized a general framework that can turn any maximizing mutual information into minimizing contrastive loss. We apply it to both the semantic clustering assignment and representation feature and propose a novel method named Deep Robust Clustering by Contrastive Learning (DRC). Different to existing methods, DRC aims to increase inter-class diver-sities and decrease intra-class diversities simultaneously and achieve more robust clustering results. Extensive experiments on six widely-adopted deep clustering benchmarks demonstrate the superiority of DRC in both stability and accuracy. e.g., attaining 71.6 state-of-the-art results.

READ FULL TEXT

page 3

page 7

research
04/03/2021

Graph Contrastive Clustering

Recently, some contrastive learning methods have been proposed to simult...
research
03/13/2023

Dynamic Clustering and Cluster Contrastive Learning for Unsupervised Person Re-identification

Unsupervised Re-ID methods aim at learning robust and discriminative fea...
research
11/14/2022

C3: Cross-instance guided Contrastive Clustering

Clustering is the task of gathering similar data samples into clusters w...
research
03/03/2021

Deep Clustering by Semantic Contrastive Learning

Whilst contrastive learning has achieved remarkable success in self-supe...
research
07/24/2021

Clustering by Maximizing Mutual Information Across Views

We propose a novel framework for image clustering that incorporates join...
research
04/15/2019

Deep Comprehensive Correlation Mining for Image Clustering

Recent developed deep unsupervised methods allow us to jointly learn rep...
research
07/08/2021

Augmented Data as an Auxiliary Plug-in Towards Categorization of Crowdsourced Heritage Data

In this paper, we propose a strategy to mitigate the problem of ineffici...

Please sign up or login with your details

Forgot password? Click here to reset