AI Paper Atlas

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

PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels

Huaxi Huang, Hui Kang, Sheng Liu, Olivier Salvado, Thierry Rakotoarivelo, Dadong Wang, Tongliang Liu

ICCV 2023 · Label-efficient and robust learning › Noisy labels · approach: Sample selection and co-training · 21 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 PES training of later layers on top of AS/PS-disentangled early stopping (ablation)PADDLES_Base · CIFAR-100 symmetric 50%test accuracy (%): 47.72 -> 59.78Improved
add PES training of later layers (ablation)PADDLES_Base · CIFAR-10 pairflip 45%test accuracy (%): 82.80 -> 89.32Improved
add phase-amplitude disentangled early stopping (without PES) (ablation)CE baseline · CIFAR-10 symmetric 50%test accuracy (%): 75.51 -> 83.40Improved
add PADDLES in place of PESsupervised confident-sample training · CIFAR-10 symmetric 20%test accuracy (%): 92.38 -> 92.43No clear effect
use PADDLES instead of PES in semi-supervised settingsemi-supervised noisy label learning · CIFAR-100 symmetric 80%test accuracy (%): 61.6 -> 62.9Improved
use PADDLES instead of SOP+CIFAR-10N Aggregate · CIFAR-10N Aggregatetest accuracy (%): 95.61 -> 95.46Hurt
train longer on phase spectrum (large T_P) before stopping (ablation)PADDLES · CIFAR-Ntest accuracyHurt
increase amplitude-spectrum stopping epoch T_A from 18 to 30 (ablation)PADDLES · CIFAR-100N Fine and CIFAR-10N Worsttest accuracyImproved
choose disentangle position after 3rd or 4th ResNet block (ablation)PADDLES · CIFAR-10 and CIFAR-100test accuracyImproved
train on phase spectrum rather than amplitude spectrum under label noise (ablation)ResNet-18 · CIFAR-10 symmetric 50%robustness to label noiseImproved

Later papers that compared with this method

1 later accepted paper reports PADDLES 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 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