AI Paper Atlas

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

O2U-Net: A Simple Noisy Label Detection Approach for Deep Neural Networks

Jinchi Huang, Lie Qu, Rongfei Jia, Binqiang Zhao

ICCV 2019 · Label-efficient and robust learning › Noisy labels · approach: Sample selection and co-training · 267 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 cyclical learning rate instead of constant learning rate for loss tracking (ablation)O2U-net detection · CIFAR-10 40% noise, ResNet-101detection precision (%): 39.96% -> 95.67%Improved
use cyclical learning rate instead of constant for loss ranking (ablation)O2U-net detection · CIFAR-100 40% noise, ResNet-101detection precision (%): 40.41% -> 92.64%Improved
remove detected top-k noisy labels before retrainingO2U-net · CIFAR-10 80% noise, ResNet-101accuracy (%): 15.91% -> 37.76%Improved
use O2U-net instead of Co-Teaching for final classifierResNet-101 · Clothing1Maccuracy (%): 78.52% -> 82.38%Improved
use O2U-net instead of CurriculumNet for final classifier9-Layer CNN · Clothing1Maccuracy (%): 73.33% -> 75.61%Improved
use O2U-net instead of MentorNet DDResNet-101 · CIFAR-10 40% noiseaccuracy (%): 88.64% -> 90.33%Improved
use cycle length 50 instead of 10 (ablation)O2U-net · CIFAR-100 80% noise, ResNet-101accuracy (%): 39.39% -> 26.96%Hurt
use cycle length 50 instead of 10 (ablation)O2U-net · CIFAR-10 80% noise, ResNet-101accuracy (%): 37.76% -> 43.41%Improved
vary cycle length (ablation)O2U-net · CIFAR-100 detectionprecisionNo clear effect
reduce cyclical-training batch size from 128 to 16 (ablation)O2U-net · 20% random noise, ResNet-101detection PR curveImproved
reduce cyclical-training batch size to 4 (ablation)O2U-net · 20% random noise, ResNet-101detection PR curveHurt
use O2U-net instead of Co-Teaching for detectionResNet-101 · CIFAR-100 40% noisedetection precision (%): 78.60% -> 92.64%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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