AI Paper Atlas

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

Detecting Corrupted Labels Without Training a Model to Predict

Zhaowei Zhu, Zihao Dong, Yang Liu

ICML 2022 · Label-efficient and robust learning › Noisy labels · approach: Instance-dependent noise modeling · 16 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
detect corrupted labels using feature-neighborhood ranking instead of training on noisy labelsSimiFeat-R vs. training-based methods · CIFAR-10 and CIFAR-100, synthetic and human noiseF1-score (%)Improved
use local neighborhood voting rather than training-based detectionSimiFeat-V vs. training-based methods · CIFAR-10 and CIFAR-100, synthetic and human noiseF1-score (%)Improved
directly use extracted features instead of fine-tuned model logitsSimiFeat vs. methods using the same CLIP extractor · CIFAR-10 and CIFAR-100F1-score (%)Mixed
add one-epoch domain-specific warmup to the feature extractor (ablation)SimiFeat on Clothing1M · Clothing1Mbest-epoch test accuracy: 72.37 -> 73.64Improved
add balanced sampling during training on selected data (ablation)SimiFeat-selected Clothing1M training set · Clothing1Mbest-epoch test accuracy: 73.64 -> 73.97Improved
filter noisy training instances before training (ablation)Clothing1M standard training · Clothing1Mbest-epoch test accuracy: 70.32 -> 72.37Improved
use CLIP features rather than ImageNet ResNet50 features for selection (ablation)SimiFeat on Clothing1M · Clothing1Mbest-epoch test accuracy: 72.37 -> 72.54Improved
use feature representations directly instead of a noisy-label-trained logit layer (ablation)SimiFeat-V vs. deep k-NN · CIFAR-10 and CIFAR-100F1-score (%)Mixed

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