AI Paper Atlas

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

NLNL: Negative Learning for Noisy Labels

Youngdong Kim, Junho Yim, Juseung Yun, Junmo Kim

ICCV 2019 · Label-efficient and robust learning › Noisy labels · approach: Sample selection and co-training · 331 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 SelPL after NL and SelNL (ablation)SelNLPL · CIFAR10 30% symm-incaccuracy (%): 92.44 -> 93.82Improved
add SelPL after NL and SelNL (ablation)SelNLPL · CIFAR10 50% symm-incaccuracy (%): 89.36 -> 91.17Improved
add SelNL between NL and SelPL (ablation)SelNLPL · CIFAR10 30% symm-incaccuracy (%): 93.41 -> 93.82Improved
add SelNL between NL and SelPL (ablation)SelNLPL · CIFAR10 50% symm-incaccuracy (%): 72.91 -> 91.17Improved
add SelNL and SelPL after NL (ablation)SelNLPL · CIFAR10 30% symm-incaccuracy (%): 87.32 -> 93.82Improved
add SelNL and SelPL after NL (filtering precision) (ablation)SelNLPL · CIFAR10 50% symm-incprecision: 50.38 -> 95.38Improved
train with NL (complementary labels) instead of PLNL · CIFAR10 30% symm-inctest accuracyImproved
provide 110 random complementary labels per image instead of one (ablation)NL · CIFAR100convergenceImproved
use proposed method instead of Truncated LqSelNLPL+pseudo labeling · CIFAR10 20% symm-excaccuracy (%): 89.70 -> 94.23Improved
use proposed method instead of JointSelNLPL+pseudo labeling · CIFAR10 40% asymm (Pre-ResNet32)accuracy (%): 91.7 -> 90.99Hurt
use proposed method instead of SemiSelNLPL+pseudo labeling · CIFAR10 60% asymm (ResNet14)accuracy (%): 75.8 -> 74.44Hurt
use proposed method at 80% symm-exc noiseSelNLPL+pseudo labeling · FashionMNIST/CIFAR 80% symm-excconvergenceHurt

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