Learning from noisy labels via discrepant collaborative training

Yan Han, Soumava Kumar Roy, Lars Petersson, Mehrtash Harandi

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    10 Citations (Scopus)

    Abstract

    Noise is ubiquitous in the world around us. Difficulty in estimating the noise within a dataset makes learning from such a dataset a difficult and challenging task. In this paper, we propose a novel and effective learning framework in order to alleviate the adverse effects of noise within a dataset. Towards this aim, we modify a collaborative training framework to utilize discrepancy constraints between respective feature extractors enabling the learning of distinct, yet discriminative features, pacifying the adverse effects of noise. Empirical results of our proposed algorithm, Discrepant Collaborative Training (DCT), achieve competitive results against several current state-of-the-art algorithms across MNIST, CIFAR10 and CIFAR100, as well as large fine-grained image classification datasets such as CUBS-200-2011 and CARS196 for different levels of noise.

    Original languageEnglish
    Title of host publicationProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages3158-3167
    Number of pages10
    ISBN (Electronic)9781728165530
    DOIs
    Publication statusPublished - Mar 2020
    Event2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020 - Snowmass Village, United States
    Duration: 1 Mar 20205 Mar 2020

    Publication series

    NameProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020

    Conference

    Conference2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020
    Country/TerritoryUnited States
    CitySnowmass Village
    Period1/03/205/03/20

    Fingerprint

    Dive into the research topics of 'Learning from noisy labels via discrepant collaborative training'. Together they form a unique fingerprint.

    Cite this