AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition

Xiaohang Zhan, Ziwei Liu, Junjie Yan, Dahua Lin, Chen Change Loy

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 85 citations (OpenAlex)

Read the paper

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 CDP with 10-fold unlabeled dataTiny NASNet-A baseline · MegaFacerank-1 identification rate: 61.78 -> 78.18Improved
add CDP with 10-fold unlabeled dataTiny NASNet-A baseline · IJB-ATPR@FPR=0.001: 75.87 -> 90.64Improved
use Inception-ResNet V2 as base model with CDPCDP · MegaFacerank-1 identification rate: 58.68 -> 81.88Improved
add CDP on top of ArcFace baselineArcFace with cleaner data · MegaFacerank-1 identification rate: 76.93% -> 83.68%Improved
add eight committee members to voting (ablation)pair voting · validation setpairwise recall: 0.680 -> 0.807Improved
add more committee members (4 to 8) to voting (ablation)pair voting · validation setpair selection precision: 0.987 -> 0.979Mixed
add affinity vector I_A to mediator input (ablation)mediator · validation setpairwise precision: 0.822 -> 0.888Improved
add neighbors distribution vector I_D to mediator input (ablation)mediator · validation setpairwise precision: 0.888 -> 0.912Improved
replace voting with mediator (ablation)8-member committee · validation setpairwise precision: 0.876 -> 0.912Improved
use heterogeneous instead of homogeneous committee (ablation)mediator · validation setpairwise precision: 0.831 -> 0.912Improved
increase k in k-NN from 10 to 40 (ablation)CDP · validation setpairwise precision: 0.940 -> 0.874Hurt
increase k in k-NN from 10 to 40 (ablation)CDP · validation setpairwise recall: 0.810 -> 0.837Improved

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