AI Paper Atlas

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

Combinatorial Inference against Label Noise

Paul Hongsuck Seo, Geeho Kim, Bohyung Han

NeurIPS 2019 · 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
replace standard flat classifier with combinatorial classification over meta-class setsResNet-50 · CUB-200 open-set high uniform noiseaccuracy (%): 70.04 -> 79.19Improved
replace standard classifier with CombClsResNet-50 · CUB-200 closed-set high uniform noiseaccuracy (%): 42.35 -> 51.90Improved
replace standard classifier with CombCls on clean dataResNet-50 · CUB-200 cleanaccuracy (%): 80.57 -> 82.80Improved
combine CombCls with Co-teachingCombCls · CUB-200 closed-set high uniform noiseaccuracy (%): 51.90 -> 62.77Improved
use q-loss (q=0.5) instead of CombCls under uniform closed-set noiseCombCls · CUB-200 closed-set high uniform noiseaccuracy (%): 60.89 vs 51.90Hurt
k-means clustering instead of random meta-class sets (ablation)CombCls · CUB-200 closed-set high uniform noiseaccuracy (%): 46.98 -> 51.90Improved
add RL-based meta-class set search (ablation)CombCls · CUB-200 open-set high uniform noiseaccuracy (%): 79.19 -> 79.98Improved
add RL-based meta-class set search (ablation)CombCls · WebVisionaccuracy (%): 83.14 -> 83.26Improved
generate meta-class sets from a high-noise dataset rather than clean data (ablation)CombCls · CUB-200 closed-setaccuracy (%): 45.40 -> 51.90Improved
generate meta-class sets from a high-noise dataset rather than clean data (ablation)CombCls · CUB-200 open-setaccuracy (%): 77.82 -> 79.19Mixed
use CombCls feature extractor for a standard classifier (ablation)Standard · CUB-200 open-set high uniform noiseaccuracy (%): 70.04 -> 78.48Improved
use CombCls feature extractor for a standard classifier (ablation)Standard · CUB-200 closed-set high uniform noiseaccuracy (%): 42.35 -> 53.83Improved

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