AI Paper Atlas

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

Learning From Noisy Data With Robust Representation Learning

Junnan Li, Caiming Xiong, Steven C.H. Hoi

ICCV 2021 · Label-efficient and robust learning › Noisy labels · approach: Contrastive learning on noisy data · 123 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 the mixup prototypical contrastive loss (ablation)RRL · CIFAR-10 Sym 50%accuracy (classifier): 85.9 -> 94.3Improved
add the mixup prototypical contrastive loss (ablation)RRL · CIFAR-100 Sym 50%accuracy (classifier): 65.6 -> 74.8Improved
add the consistency contrastive loss (ablation)RRL · CIFAR-10 Sym 50%accuracy (classifier): 93.7 -> 94.3Improved
add the consistency contrastive loss (ablation)RRL · CIFAR-100 Sym 50%accuracy (classifier): 71.9 -> 74.8Improved
add the consistency contrastive loss (ablation)RRL · CIFAR-10 Sym 50% + image corruptionaccuracy (classifier): 89.4 -> 91.4Improved
add the reconstruction loss (ablation)RRL · CIFAR-10 Sym 50%accuracy (classifier): 93.3 -> 94.3Improved
add the reconstruction loss (ablation)RRL · CIFAR-100 Sym 50%accuracy (classifier): 73.2 -> 74.8Improved
add mixup augmentation (ablation)RRL · CIFAR-10 Sym 50%accuracy (classifier): 89.5 -> 94.3Improved
add mixup augmentation (ablation)RRL · CIFAR-100 Sym 50%accuracy (classifier): 69.3 -> 74.8Improved
use AugMix strong augmentation instead of standard augmentation (ablation)RRL · CIFAR-100 Sym 50%accuracy (classifier): 74.5 -> 74.8Improved
classify with knn on embeddings instead of the softmax classifierRRL · CIFAR-100 Sym 20%accuracy: 79.1 -> 79.4Improved
add noise cleaning with smooth neighbors (ablation)RRL · WebVision (mini) valtop-1 accuracy: 75.5 -> 76.3Improved

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