AI Paper Atlas

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

Co-Mining: Deep Face Recognition With Noisy Labels

Xiaobo Wang, Shuo Wang, Jun Wang, Hailin Shi, Tao Mei

ICCV 2019 · Label-efficient and robust learning › Noisy labels · approach: Sample selection and co-training · 121 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 noisy labels detection (NLD) (ablation)Arc-Softmax baseline · CASIA-Clean-R synthetic symmetric noise 0.1average accuracy (%): 90.90 -> 91.11Improved
add high-confidence clean faces exchanging (HCCFE) (ablation)Arc-Softmax + NLD · CASIA-Clean-R synthetic symmetric noise 0.1average accuracy (%): 91.11 -> 91.39Improved
add clean faces re-weighting (CFR) (ablation)Arc-Softmax + NLD + HCCFE · CASIA-Clean-R synthetic symmetric noise 0.1average accuracy (%): 91.39 -> 92.16Improved
add noisy labels detection (NLD) (ablation)Arc-Softmax baseline · CASIA-Clean-R synthetic symmetric noise 0.2average accuracy (%): 69.70 -> 77.04Improved
add high-confidence clean faces exchanging (HCCFE) (ablation)Arc-Softmax + NLD · CASIA-Clean-R synthetic symmetric noise 0.2average accuracy (%): 77.04 -> 78.58Improved
add clean faces re-weighting (CFR) (ablation)Arc-Softmax + NLD + HCCFE · CASIA-Clean-R synthetic symmetric noise 0.2average accuracy (%): 78.58 -> 83.95Improved
add noisy labels detection (NLD) (ablation)Arc-Softmax baseline · CASIA-Clean-R synthetic symmetric noise 0.3average accuracy (%): 58.81 -> 67.24Improved
add high-confidence clean faces exchanging (HCCFE) (ablation)Arc-Softmax + NLD · CASIA-Clean-R synthetic symmetric noise 0.3average accuracy (%): 67.24 -> 72.92Improved
add clean faces re-weighting (CFR) (ablation)Arc-Softmax + NLD + HCCFE · CASIA-Clean-R synthetic symmetric noise 0.3average accuracy (%): 72.92 -> 81.32Improved
train on cleaned CASIA instead of noisy originalArc-Softmax baseline · CASIA (LFW/CALFW/CPLFW/AgeDB/CFP)average accuracy (%): 91.05 -> 91.73Improved
apply Co-Mining instead of baselineMobileFaceNet + Arc-Softmax · Trained on VggFace2-R, CALFW/CPLFW/AgeDB/CFPaverage accuracy (%): 91.18 -> 92.07Improved
apply prior noisy-label methods (MN, DC, CT, CT+) instead of baselineMobileFaceNet + Arc-Softmax · Trained on VggFace2-R, CALFW/CPLFW/AgeDB/CFPaverage accuracy (%): 91.18 -> 90.62No clear effect

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