Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Multi-objective interpolation training for robustness to label noise

Ortego, Diego orcid logoORCID: 0000-0002-1011-3610, Arazo, Eric, Albert, Paul, McGuinness, Kevin orcid logoORCID: 0000-0003-1336-6477 and O'Connor, Noel E. orcid logoORCID: 0000-0002-4033-9135 (2021) Multi-objective interpolation training for robustness to label noise. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 20-25 June 2021, Nashville, TN, USA + Virtual.

Deep neural networks trained with standard cross-entropy loss memorize noisy labels, which degrades their performance. Most research to mitigate this memorization proposes new robust classification loss functions. Conversely, we propose a Multi-Objective Interpolation Training (MOIT) approach that jointly exploits contrastive learning and classification to mutually help each other and boost performance against label noise. We show that standard supervised contrastive learning degrades in the presence of label noise and propose an interpolation training strategy to mitigate this behavior. We further propose a novel label noise detection method that exploits the robust feature representations learned via contrastive learning to estimate per-sample soft-labels whose disagreements with the original labels accurately identify noisy samples. This detection allows treating noisy samples as unlabeled and training a classifier in a semi-supervised manner to prevent noise memorization and improve representation learning. We further propose MOIT+, a refinement of MOIT by fine-tuning on detected clean samples. Hyperparameter and ablation studies verify the key components of our method. Experiments on synthetic and real-world noise benchmarks demonstrate that MOIT/MOIT+ achieves state-of-the-art results. Code is available at \url{https://git.io/JI40X}.
Item Type:Conference or Workshop Item (Poster)
Event Type:Conference
Subjects:Computer Science > Artificial intelligence
Computer Science > Image processing
Computer Science > Machine learning
Engineering > Signal processing
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Institutes and Centres > INSIGHT Centre for Data Analytics
Published in: 2021 Conference on Computer Vision and Pattern Recognition (CVPR). . IEEE.
Official URL:https://doi.org/10.1109/CVPR46437.2021.00654
Copyright Information:© 2021 The Authors
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Science Foundation Ireland (SFI) under grant number SFI/15/SIRG/3283 and SFI/12/RC/2289 P2.
ID Code:25597
Deposited On:17 Jun 2021 15:40 by Diego Ortego Hernández . Last Modified 04 Nov 2021 14:58

Full text available as:

[thumbnail of 04337.pdf]
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader


Downloads per month over past year

Archive Staff Only: edit this record