AI Paper Atlas

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

Robust Inference via Generative Classifiers for Handling Noisy Labels

Kimin Lee, Sukmin Yun, Kibok Lee, Honglak Lee, Bo Li, Jinwoo Shin

ICML 2019 · Label-efficient and robust learning › Noisy labels · approach: Sample selection and co-training · 56 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 softmax inference with ensemble RoGResNet · CIFAR-10, uniform noisetest accuracy: 80.88 / 80.88 -> 84.62; 61.98 -> 75.28; 39.96 -> 54.57Improved
Replace softmax inference with ensemble RoGResNet · CIFAR-100, uniform noisetest accuracy: 64.43 / 68.29; 48.62 / 60.76; 27.57 / 48.42Improved
Replace softmax inference with ensemble RoGResNet · SVHN, uniform noisetest accuracy: 83.52 / 91.67; 72.89 / 87.16; 61.23 / 80.52Improved
Add MCD parameter estimation instead of naive sample estimation (ablation)Generative classifier · CIFAR-10, Uniform (40%), DenseNettest accuracy: 76.75 -> 80.27Improved
Add layer-wise ensemble to sample-estimated generative classifiers (ablation)Generative classifier · CIFAR-10, Uniform (40%), DenseNettest accuracy: 76.75 -> 81.27Improved
Add layer-wise ensemble to MCD-estimated generative classifiers (ablation)RoG · CIFAR-10, Uniform (40%), DenseNettest accuracy: 80.27 -> 81.83Improved
Add MCD estimation instead of sample estimation (ablation)Ensemble generative classifier · CIFAR-10, Uniform (40%), DenseNettest accuracy: 81.27 -> 81.83Improved
Add RoG inference to Co-teachingCo-teaching · CIFAR-100, Flip (45%)test accuracy: 33.34 -> 43.18Improved
Replace softmax inference with RoGDenseNet · CIFAR-100, open-set noisetest accuracy: 79.01 -> 83.37Improved
Use LDA tied covariance rather than identity covariance (ablation)Generative classifier · CIFAR-10, uniform noise, ResNet-34test accuracyImproved

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