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

Files

hdl_140263.pdf (1.36 MB)
  (Published version)

Date

2023

Authors

Sachdeva, R.
Cordeiro, F.R.
Belagiannis, V.
Reid, I.
Carneiro, G.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Journal article

Citation

Pattern Recognition, 2023; 134:109121-1-109121-10

Statement of Responsibility

Ragav Sachdeva, Filipe Rolim Cordeiro, Vasileios Belagiannis, Ian Reid, Gustavo Carneiro

Conference Name

Abstract

We 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.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

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/)

License

Call number

Persistent link to this record