Show simple item record

dc.contributor.authorBiswas, Momojit
dc.contributor.authorBuckchash, Himanshu
dc.contributor.authorPrasad, Dilip Kumar
dc.date.accessioned2024-10-10T08:36:44Z
dc.date.available2024-10-10T08:36:44Z
dc.date.issued2024-05-11
dc.description.abstractNearest neighbor (NN) sampling provides more semantic variations than predefined transformations for selfsupervised learning (SSL) based image recognition problems. However, its performance is restricted by the quality of the support set, which holds positive samples for the contrastive loss. In this work, we show that the quality of the support set plays a crucial role in any nearest neighbor based method for SSL. We then provide a refined baseline (pNNCLR) to the nearest neighbor based SSL approach (NNCLR). To this end, we introduce pseudo nearest neighbors (pNN) to control the quality of the support set, wherein, rather than sampling the nearest neighbors, we sample in the vicinity of hard nearest neighbors by varying the magnitude of the resultant vector and employing a stochastic sampling strategy to improve the performance. Additionally, to stabilize the effects of uncertainty in NN-based learning, we employ a smooth-weight-update approach for training the proposed network. Evaluation of the proposed method on multiple public image recognition and medical image recognition datasets shows that it performs up to 8 percent better than the baseline nearest neighbor method, and is comparable to other previously proposed SSL methods. The code is available at <a href=https://github.com/mb16biswas/pnnclr>https://github.com/mb16biswas/pnnclr</a>en_US
dc.identifier.citationBiswas, Buckchash, Prasad. pNNCLR: Stochastic pseudo neighborhoods for contrastive learning based unsupervised representation learning problems. Neurocomputing. 2024;593en_US
dc.identifier.cristinIDFRIDAID 2271339
dc.identifier.doi10.1016/j.neucom.2024.127810
dc.identifier.issn0925-2312
dc.identifier.issn1872-8286
dc.identifier.urihttps://hdl.handle.net/10037/35169
dc.language.isoengen_US
dc.publisherElsevieren_US
dc.relation.journalNeurocomputing
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/H2020/964800/EU/OrganVision: Technology for real-time visualizing and modelling of fundamental process in living organoids towards new insights into organ-specific health, disease, and recovery/OrganVision/en_US
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/European Research Council/101123485/EU/Sperm filtration for improved success rate of assisted reproduction technology/Spermotile/en_US
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2024 The Author(s)en_US
dc.rights.urihttps://creativecommons.org/licenses/by/4.0en_US
dc.rightsAttribution 4.0 International (CC BY 4.0)en_US
dc.titlepNNCLR: Stochastic pseudo neighborhoods for contrastive learning based unsupervised representation learning problemsen_US
dc.type.versionpublishedVersionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record

Attribution 4.0 International (CC BY 4.0)
Except where otherwise noted, this item's license is described as Attribution 4.0 International (CC BY 4.0)