AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

DivideMix: Learning with Noisy Labels as Semi-supervised Learning

Junnan Li, Richard Socher, Steven C.H. Hoi

ICLR 2020 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines · 524 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use DivideMix instead of M-correctionCIFAR-10 with symmetric label noise · CIFAR-10, symmetric noise at 20%, 50%, 80%, and 90%Best test accuracy (%): 94.0 -> 96.1; 92.0 -> 94.6; 86.8 -> 93.2; 69.1 -> 76.0Improved
Use DivideMix instead of M-correction at 20% and 50%, and Meta-Learning at 80% and 90%CIFAR-100 with symmetric label noise · CIFAR-100, symmetric noise at 20%, 50%, 80%, and 90%Best test accuracy (%): 73.9 -> 77.3; 66.1 -> 74.6; 42.4 -> 60.2; 24.3 -> 31.5Improved
Use DivideMix instead of Meta-LearningCIFAR-10 with asymmetric label noise · CIFAR-10, asymmetric noise 40%Best test accuracy (%): 89.2 -> 93.4Improved
Use DivideMix instead of P-correctionClothing1M · Clothing1MTest accuracy (%): 73.49 -> 74.76Improved
Use DivideMix instead of Iterative-CVWebVision and ILSVRC12 validation · WebVision and ILSVRC12 validationTop-1 accuracy (%): 65.24 -> 77.32; 61.60 -> 75.20Improved
Use an ensemble of both networks at test time instead of only network θ(1) (ablation)DivideMix · CIFAR-10 and CIFAR-100 label-noise benchmarksTest accuracy (%)Improved
Use co-training instead of self-divide (ablation)DivideMix · CIFAR-100, symmetric noise 90%Best test accuracy (%): 27.7 -> 31.5Improved
Add label refinement (ablation)DivideMix · CIFAR-10, asymmetric noise 40%Best test accuracy (%): 87.7 -> 93.4Improved
Add input augmentation (ablation)DivideMix · CIFAR-10, asymmetric noise 40%Best test accuracy (%): 89.5 -> 93.4Improved
Replace co-divide with self-divide and use original MixMatch (ablation)DivideMix · CIFAR-100, symmetric noise 90%Best test accuracy (%): 25.0 -> 31.5Hurt

Later papers that compared with this method

68 later accepted papers report DivideMix as a baseline in their results tables; 65 of them report a better number on most of the results they share with it.

60 more not listed.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy