AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning

Jun Shu, Xiang Yuan, Deyu Meng, Zongben Xu

TPAMI 2023 · Label-efficient and robust learning › Noisy labels · approach: Sample selection and co-training · 72 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
add class-aware weighting (CMW-Net) in place of single class-agnostic MW-NetMW-Net · CIFAR-10-LT (imbalance 200)top-1 error (%): 32.80 -> 27.80Improved
add class-aware weighting (CMW-Net) in place of MW-NetMW-Net · CIFAR-100-LT (imbalance 100)top-1 error (%): 58.39 -> 55.25Improved
add CMW-Net on top of LDAM lossLDAM · CIFAR-10-LT (imbalance 100)top-1 error (%): 26.65 -> 19.95Improved
add CMW-Net on top of SADESADE · CIFAR-10-LT (imbalance 100)top-1 error (%): 16.78 -> 16.04Improved
use class-aware weighting in a balanced dataset (imbalance factor 1)MW-Net · CIFAR-10-LT (imbalance 1)top-1 error (%): 7.19 -> 8.30Hurt
use CMW-Net instead of MW-Net under asymmetric noiseMW-Net · CIFAR-10 asymmetric noise 0.8test accuracy (%): 58.29 -> 87.50Improved
add soft label supervision (pseudo-labels) to CMW-Net (ablation)CMW-Net · CIFAR-10 symmetric noise 0.8test accuracy (%): 64.80 -> 92.10Improved
add soft label supervision to CMW-Net (ablation)CMW-Net · CIFAR-100 asymmetric noise 0.8test accuracy (%): 17.41 -> 18.34Improved
add soft label supervision to CMW-Net (ablation)CMW-Net · Animal-10Ntest accuracy (%): 80.9 -> 84.7Improved
add soft label supervision to CMW-Net (ablation)CMW-Net · CIFAR-10 feature-dependent Type-I 35%test accuracy (%): 82.27 -> 84.23Improved
add self-supervised warm-up and consistency regularization (SL+) (ablation)CMW-Net-SL · CIFAR-100 symmetric noise 0.9test accuracy (%): 21.2 -> 64.6Improved
use CMW-Net-SL instead of DivideMix at extreme symmetric noiseDivideMix · CIFAR-10 symmetric noise 0.8test accuracy (%): 92.90 -> 92.10Hurt

Later papers that compared with this method

1 later accepted paper reports CMW-Net as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

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