AI Paper Atlas

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

ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks

Xinshao Wang, Yang Hua, Elyor Kodirov, David A. Clifton, Neil M. Robertson

CVPR 2021 · Label-efficient and robust learning › Noisy labels · approach: Noisy cross-modal hashing and multi-label · 63 citations (OpenAlex)

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 progressive, entropy-dependent self label correction instead of CCEResNet-44 · CIFAR-100 asymmetric noise 40%accuracy (%): 59.5 -> 67.9Improved
Use progressive, entropy-dependent self label correction instead of CCEResNet-44 · CIFAR-100 symmetric noise 60%accuracy (%): 37.9 -> 47.7Improved
Use progressive, entropy-dependent self label correction instead of CCEResNet-50 · Clothing 1Maccuracy (%): 72.2 -> 73.4Improved
Use progressive, entropy-dependent self label correction instead of CCEResNet-50 · ImageNet 2012accuracy (%): 75.5 -> 76.0Improved
Increase ProSelfLC growth parameter B from 8 to 10 (ablation)ProSelfLC · CIFAR-100 clean testaccuracy (%): 70.1 -> 70.3Improved
Increase ProSelfLC growth parameter B from 10 to 12 (ablation)ProSelfLC · CIFAR-100 clean testaccuracy (%): 70.3 -> 69.8Hurt
Set B=16 rather than B=8 (ablation)ProSelfLC · CIFAR-100 symmetric noise 60%accuracy (%): 47.7 -> 32.3Hurt
Raise fixed self-correction weight ε from 0.125 to 0.50 (ablation)Boot-soft · CIFAR-100 clean testaccuracy (%): 68.9 -> 69.1Improved
Raise label-smoothing weight ε from 0.125 to 0.50 (ablation)LS · CIFAR-100 symmetric noise 60%accuracy (%): 39.1 -> 46.5Improved
Raise confidence-penalty weight ε from 0.125 to 0.50 (ablation)CP · CIFAR-100 symmetric noise 60%accuracy (%): 39.6 -> 44.1Improved
Use ProSelfLC rather than CCECIFAR-100 standard training · CIFAR-100 clean testaccuracy (%): 69.0 -> 70.3Improved

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