dc.contributor.author | Huang, J | |
dc.contributor.author | Dong, Q | |
dc.contributor.author | Gong, S | |
dc.contributor.author | Zhu, X | |
dc.contributor.author | Intelligence, AAA | |
dc.date.accessioned | 2021-09-22T09:29:05Z | |
dc.date.available | 2021-09-22T09:29:05Z | |
dc.date.issued | 2020 | |
dc.identifier.issn | 2159-5399 | |
dc.identifier.uri | https://qmro.qmul.ac.uk/xmlui/handle/123456789/74214 | |
dc.description.abstract | Convolutional neural networks (CNNs) have achieved unprecedented success in a variety of computer vision tasks. However, they usually rely on supervised model learning with the need for massive labelled training data, limiting dramatically their usability and deployability in real-world scenarios without any labelling budget. In this work, we introduce a general-purpose unsupervised deep learning approach to deriving discriminative feature representations. It is based on self-discovering semantically consistent groups of unlabelled training samples with the same class concepts through a progressive affinity diffusion process. Extensive experiments on object image classification and clustering show the performance superiority of the proposed method over the state-of-the-art unsupervised learning models using six common image recognition benchmarks including MNIST, SVHN, STL10, CIFAR10, CIFAR100 and ImageNet. | en_US |
dc.format.extent | 11029 - 11036 | |
dc.publisher | Association for the Advancement of Artificial Intelligence | en_US |
dc.title | Unsupervised Deep Learning via Affinity Diffusion | en_US |
dc.type | Conference Proceeding | en_US |
dc.rights.holder | © 2020, Association for the Advancement of Artificial Intelligence | |
pubs.author-url | http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000668126803059&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=612ae0d773dcbdba3046f6df545e9f6a | en_US |
pubs.notes | Not known | en_US |
pubs.publication-status | Published | en_US |
pubs.volume | 34 | en_US |
rioxxterms.funder | Default funder | en_US |
rioxxterms.identifier.project | Default project | en_US |