Consensus Clustering With Unsupervised Representation Learning

Recent advances in deep clustering and unsupervised representation learning are based on the idea that different views of an input image (generated through data augmentation techniques) must either be closer in the representation space, or have a similar cluster assignment. Bootstrap Your Own Latent...

Full description

Saved in:
Bibliographic Details
Main Authors: Regatti, Jayanth Reddy, Deshmukh, Aniket Anand, Manavoglu, Eren, Dogan, Urun
Format: Conference Proceeding
Language:English
Subjects:
Classification algorithms
Clustering
Clustering algorithms
Computer vision
consensus clustering
Image classification
Neural networks
Partitioning algorithms
Protocols
representation learning
unsupervised learning
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent advances in deep clustering and unsupervised representation learning are based on the idea that different views of an input image (generated through data augmentation techniques) must either be closer in the representation space, or have a similar cluster assignment. Bootstrap Your Own Latent (BYOL) is one such representation learning algorithm that has achieved state-of-the-art results in self-supervised image classification on ImageNet under the linear evaluation protocol. However, the utility of the learnt features of BYOL to perform clustering is not explored. In this work, we study the clustering ability of BYOL and observe that features learnt using BYOL may not be optimal for clustering. We propose a novel consensus clustering based loss function, and train BYOL with the proposed loss in an end-to-end way that improves the clustering ability and outperforms similar clustering based methods on some popular computer vision datasets.
ISSN:2161-4407
DOI:10.1109/IJCNN52387.2021.9533714