Consensus Clustering With Unsupervised Representation Learning

Autor:	Regatti, Jayanth Reddy, Deshmukh, Aniket Anand, Manavoglu, Eren, Dogan, Urun
Rok vydání:	2020
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted by the 2021 International Joint Conference on Neural Networks (IJCNN 2021)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2010.01245 Zobrazit plný text záznamu View this record from Arxiv