AI Paper Atlas

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

Searching for Robustness: Loss Learning for Noisy Classification Tasks

Boyan Gao, Henry Gouk, Timothy M. Hospedales

ICCV 2021 · Label-efficient and robust learning › Noisy labels · approach: Noise-aware loss and pairwise methods · 14 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
replace cross-entropy with the learned Taylor loss (DR)general-purpose loss · Average rank, 80% symmetric noise (10 arch/dataset pairs, general loss)average rank: 6.4 -> 2.0Improved
replace cross-entropy with the learned Taylor loss (AR)general-purpose loss · Average rank, 40% asymmetric noise (10 arch/dataset pairs, general loss)average rank: 5.0 -> 1.6Improved
dataset randomization instead of architecture randomization during meta-learning (ablation)Taylor loss · Average rank, 80% symmetric noise (10 arch/dataset pairs, general loss)average rank: 2.4 -> 2.0Mixed
dataset randomization instead of architecture randomization during meta-learning (ablation)Taylor loss · Average rank, 40% asymmetric noise (10 arch/dataset pairs, general loss)average rank: 1.6 -> 3.0Mixed
apply learned Taylor loss instead of CE on real noisy labelsResNet-18 · Clothing1Mtest accuracy: 66.88 -> 70.09Improved
learned loss trained under 40% asymmetric vs 80% symmetric noise, transferred to Clothing1MTaylor loss · Clothing1Mtest accuracy: 68.85 -> 70.09Mixed
plug-in Taylor loss vs multi-network JoCoRResNet-18 · Clothing1Mtest accuracy: 69.79 -> 70.09Improved
train the loss specifically for the target dataset using a clean subsetTaylor loss · MNIST Sym-80% (JoCoR net)accuracy: 84.89 -> 89.88Improved
train the loss specifically for the target dataset using a clean subsetTaylor loss · CIFAR-100 Sym-80% (JoCoR net)accuracy: 15.49 -> 20.20Improved
use a different Taylor polynomial order (2, 3, 4 or 5) (ablation)Taylor loss · MNIST/KMNIST/CIFAR-10 linear classifieraccuracyNo clear effect
apply loss trained at 80% symmetric noise to other noise levelsTaylor loss · 2MLP-MNIST, 4CNN-MNIST, VGG11-CIFAR10accuracyImproved

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