AI Paper Atlas

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

Tackling Noisy Labels With Network Parameter Additive Decomposition

Jingyi Wang, Xiaobo Xia, Long Lan, Xinghao Wu, Jun Yu, Wenjing Yang, Bo Han, Tongliang Liu

TPAMI 2024 · Label-efficient and robust learning › Noisy labels · approach: Sample selection and co-training · 24 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 parameter decomposition alone (no constraints) (ablation)Standard · CIFAR-10 (Sym. 20%)test accuracy (%): 90.19 -> 90.09No clear effect
add constraint on gamma to parameter decomposition (ablation)PD · CIFAR-10 (Sym. 40%)test accuracy (%): 86.63 -> 87.68Improved
add constraint on sigma to PD + gamma constraint (ablation)PD + gamma · CIFAR-10 (Sym. 40%)test accuracy (%): 87.68 -> 87.83Improved
add constraint on gamma to parameter decomposition (ablation)PD · CIFAR-100 (Sym. 20%)test accuracy (%): 66.31 -> 68.39Improved
add constraint on sigma to PD + gamma constraint (ablation)PD + gamma · CIFAR-100 (Sym. 20%)test accuracy (%): 68.39 -> 69.46Improved
add parameter decomposition alone (no constraints) (ablation)Standard · CIFAR-100 (Sym. 40%)test accuracy (%): 60.58 -> 60.29Hurt
use power function for decreasing constraint over constant or other schedules (ablation)TNLPAD · CIFAR-10 / F-MNISTtest accuracy (%)Improved
use constant constraint function (ablation)TNLPAD · CIFAR-10 / F-MNISTtest accuracy (%)No clear effect
add TNLPAD to SelfSelf · CIFAR-10 (Sym. 40%)test accuracy (%): 88.67 -> 89.47Improved
add TNLPAD to DivideMixDivideMix · CIFAR-10 (Sym. 20%)test accuracy (%): 96.10 -> 95.99Hurt
add TNLPAD to DivideMixDivideMix · CIFAR-10 (Asym. 40%)test accuracy (%): 92.16 -> 92.54Improved
use TNLPAD instead of Standard on Clothing1MStandard · Clothing1Mtest accuracy (%): 68.98 -> 71.51Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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