English

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

Computer Vision and Pattern Recognition 2022-10-18 v3 Machine Learning

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 non-severe 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.

Keywords

Cite

@article{arxiv.2103.11395,
  title  = {ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learning},
  author = {Ragav Sachdeva and Filipe R Cordeiro and Vasileios Belagiannis and Ian Reid and Gustavo Carneiro},
  journal= {arXiv preprint arXiv:2103.11395},
  year   = {2022}
}

Comments

Paper accepted at Pattern Recognition

R2 v1 2026-06-24T00:23:45.703Z