Computer Vision publications

Permanent URI for this collection

https://hdl.handle.net/2440/15002

Browse

Browsing Computer Vision publications by Author "Carneiro, G."

Now showing 1 - 1 of 1
  • No Thumbnail Available
    ItemOpen Access
    ScanMix : Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learning
    (Elsevier BV, 2023) Sachdeva, R.; Cordeiro, F.R.; Belagiannis, V.; Reid, I.; Carneiro, G.
    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.