Papers › Correlated Input-Dependent Label Noise in Large-Scale Image Classification

Correlated Input-Dependent Label Noise in Large-Scale Image Classification

19 May 2021CVPR 2021 1arXiv:2105.10305archive 2025-07-28

Mark Collier, Basil Mustafa, Efi Kokiopoulou, Rodolphe Jenatton, Jesse Berent

Large scale image classification datasets often contain noisy labels. We take a principled probabilistic approach to modelling input-dependent, also known as heteroscedastic, label noise in these datasets. We place a multivariate Normal distributed latent variable on the final hidden layer of a neural network classifier. The covariance matrix of this latent variable, models the aleatoric uncertainty due to label noise. We demonstrate that the learned covariance structure captures known sources of label noise between semantically similar and co-occurring classes. Compared to standard neural network training and other baselines, we show significantly improved accuracy on Imagenet ILSVRC 2012 79.3% (+2.6%), Imagenet-21k 47.0% (+1.1%) and JFT 64.7% (+1.6%). We set a new state-of-the-art result on WebVision 1.0 with 76.6% top-1 accuracy. These datasets range from over 1M to over 300M training examples and from 1k classes to more than 21k classes. Our method is simple to use, and we provide an implementation that is a drop-in replacement for the final fully-connected layer in a deep classifier.

PaperPDFConference PDF

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClassificationImage Classificationimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet Heteroscedastic (InceptionResNet-v2) Top 1 Accuracy 68.6% #1031 of 1060 Archive leaderboard report
Image Classification WebVision-1000 Heteroscedastic (InceptionResNet-v2) Top-1 Accuracy 76.6% #5 of 16 Archive leaderboard report
Image Classification WebVision-1000 Heteroscedastic (InceptionResNet-v2) Top-5 Accuracy 92.1% #5 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections