ScanMix : Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learning

Simple item page
dc.contributor.authorSachdeva, R.
dc.contributor.authorCordeiro, F.R.
dc.contributor.authorBelagiannis, V.
dc.contributor.authorReid, I.
dc.contributor.authorCarneiro, G.
dc.date.issued2023
dc.description.abstractWe propose a new training algorithm, ScanMix, that explores semantic clustering and semi-supervised learning (SSL) to allow superior robustness to severe label noise and competitive robustness to nonsevere label noise problems, in comparison to the state of the art (SOTA) methods. ScanMix is based on the expectation maximisation framework, where the E-step estimates the latent variable to cluster the training images based on their appearance and classification results, and the M-step optimises the SSL classification and learns effective feature representations via semantic clustering. We present a theoretical result that shows the correctness and convergence of ScanMix, and an empirical result that shows that ScanMix has SOTA results on CIFAR-10/-100 (with symmetric, asymmetric and semantic label noise), Red Mini-ImageNet (from the Controlled Noisy Web Labels), Clothing1M and WebVision. In all benchmarks with severe label noise, our results are competitive to the current SOTA.
dc.description.statementofresponsibilityRagav Sachdeva, Filipe Rolim Cordeiro, Vasileios Belagiannis, Ian Reid, Gustavo Carneiro
dc.identifier.citationPattern Recognition, 2023; 134:109121-1-109121-10
dc.identifier.doi10.1016/j.patcog.2022.109121
dc.identifier.issn0031-3203
dc.identifier.issn1873-5142
dc.identifier.orcidReid, I. [0000-0001-7790-6423]
dc.identifier.orcidCarneiro, G. [0000-0002-5571-6220]
dc.identifier.urihttps://hdl.handle.net/2440/140263
dc.language.isoen
dc.publisherElsevier BV
dc.relation.granthttp://purl.org/au-research/grants/arc/FT190100525
dc.rights© 2022 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/)
dc.source.urihttps://doi.org/10.1016/j.patcog.2022.109121
dc.subjectNoisy label learning; Semi-supervised learning; Semantic clustering; Self-supervised Learning; Expectation maximisation
dc.titleScanMix : Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learning
dc.typeJournal article
pubs.publication-statusPublished

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
hdl_140263.pdf
Size:
1.36 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections

Computer Vision publications