AI Paper Atlas

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

Wasserstein Adversarial Regularization for Learning With Label Noise

Kilian Fatras, Bharath Bhushan Damodaran, Sylvain Lobry, Rémi Flamary, Devis Tuia, Nicolas Courty

TPAMI 2021 · Label-efficient and robust learning › Noisy labels · approach: Sample selection and co-training · 31 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
use word2vec-derived Wasserstein ground cost instead of KL divergence (AR) (ablation)adversarial regularization · CIFAR-10 (40% noise)test accuracy: 81.98 -> 84.76Improved
use word2vec-derived Wasserstein ground cost instead of KL divergence (AR) (ablation)adversarial regularization · CIFAR-100 (40% noise)test accuracy: 55.75 -> 58.86Improved
use word2vec-derived Wasserstein ground cost instead of KL divergence (AR) (ablation)adversarial regularization · Fashion-MNIST (40% noise)test accuracy: 89.74 -> 90.41Improved
use word2vec ground cost instead of uninformative 0-1 ground cost (ablation)WAR · CIFAR-10 (40% noise)test accuracy: 74.15 -> 84.76Improved
use word2vec ground cost instead of uninformative 0-1 ground cost (ablation)WAR · CIFAR-100 (40% noise)test accuracy: 51.00 -> 58.86Improved
use word2vec ground cost instead of pretrained-CNN centroid ground cost (ablation)WAR · CIFAR-10 (40% noise)test accuracy: 85.08 -> 84.76Hurt
use word2vec ground cost instead of pretrained-CNN centroid ground cost (ablation)WAR · CIFAR-100 (40% noise)test accuracy: 55.79 -> 58.86Improved
raise beta from 5 to 20 in adversarial regularization (KL) (ablation)AR · CIFAR-10 (40% noise)test accuracy: 81.37 -> 57.36Hurt
raise beta from 5 to 20 (ablation)WAR_w2v · CIFAR-10 (40% noise)test accuracy: 80.16 -> 86.73Improved
raise beta from 10 to 20 (ablation)WAR_embed · CIFAR-10 (40% noise)test accuracy: 85.08 -> 80.36Hurt
use WAR_w2v instead of CCE under 40% label noise9-layer CNN · CIFAR-100test accuracy: 42.45 -> 58.86Improved
use WAR_w2v instead of Pencil with clean labels (0% noise)9-layer CNN · CIFAR-100test accuracy: 63.32 -> 68.16Improved

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