AI Paper Atlas

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

Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels

Ganlong Zhao, Guanbin Li, Yipeng Qin, Feng Liu, Yizhou Yu

ECCV 2022 · Label-efficient and robust learning › Noisy labels · approach: Noise-aware loss and pairwise methods · 37 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 feature clustering (stage 1) to the CE baseline (ablation)CE baseline · CIFAR-100 (eta=0.6)accuracy (%): 25.68 -> 53.60Improved
add consistency classification (stage 2) to the CE baseline (ablation)CE baseline · CIFAR-100 (eta=0.6)accuracy (%): 25.68 -> 51.41Improved
add consistency classification on top of feature clustering (ablation)Ours · CIFAR-100 (eta=0.6)accuracy (%): 53.60 -> 59.40Improved
add feature clustering on top of consistency classification (ablation)Ours · CIFAR-100 (eta=0.6)accuracy (%): 51.41 -> 59.40Improved
add feature clustering (stage 1) to the CE baseline (ablation)CE baseline · Clothing1Maccuracy (%): 68.94 -> 73.32Improved
add consistency classification (stage 2) to the CE baseline (ablation)CE baseline · Clothing1Maccuracy (%): 68.94 -> 74.26Improved
add consistency classification on top of feature clustering (ablation)Ours · Clothing1Maccuracy (%): 73.32 -> 75.40Improved
add feature clustering on top of consistency classification (ablation)Ours · Clothing1Maccuracy (%): 74.26 -> 75.40Improved
replace DivideMix with the proposed methodDivideMix · Inst. CIFAR10 (eta=0.6)accuracy (%): 85.50 -> 94.95Improved
replace DivideMix with the proposed methodDivideMix · Inst. CIFAR100 (eta=0.6)accuracy (%): 46.72 -> 59.40Improved
replace DivideMix with the proposed methodDivideMix · Inst. CIFAR10 (eta=0.4)accuracy (%): 95.07 -> 94.97Hurt
replace DivideMix with the proposed methodDivideMix · Clothing1Maccuracy (%): 74.76 -> 75.40Improved

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