AI Paper Atlas

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

Kinship Identification through Joint Learning using Kinship Verification Ensembles

Wei Wang, Shaodi You, Theo Gevers

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 23 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 joint learning of verification and identification (JLNet vs Multi-class Net)Multi-class Net · KinfaceWII Mixed Kin-Type setaccuracy: 0.5225 -> 0.5790Improved
add joint learning (JLNet vs Ensemble Net)Ensemble Net · KinfaceWI Mixed Kin-Type setaccuracy: 0.4887 -> 0.5993Improved
add backpropagation of multiple outputs during joint training (ablation)JLNet · KinfaceWI Mixed Kin-Type setaccuracy: 0.5487 -> 0.5993Improved
add backpropagation of multiple outputs during joint training (ablation)JLNet · KinfaceWII Mixed Kin-Type setmacro F1: 0.4648 -> 0.5343Improved
combine verification and multi-class outputs at test time instead of multiple output only (ablation)JLNet · KinfaceWI Mixed Kin-Type setmacro F1: 0.5507 -> 0.5506No clear effect
combine verification and multi-class outputs at test time instead of multiple output only (ablation)JLNet · KinfaceWI Real-Scenario setaccuracy: 0.6681 -> 0.7439Improved
add backpropagation of multiple outputs during joint training (ablation)JLNet · KinfaceWII Real-Scenario setaccuracy: 0.5730 -> 0.7398Improved
train verification models on Mixed set instead of independent sets (Ensemble Net vs Ensemble Net*)Ensemble Net · KinfaceWI Mixed Kin-Type setmacro F1: 0.3240 -> 0.4837Improved
train verification models on Mixed set instead of independent setsEnsemble Net · KinfaceWI Independent Kin-Type set (verification)mean accuracy: 0.7021 -> 0.6224Hurt
JLNet instead of Ensemble Net* for verification on independent setEnsemble Net* · KinfaceWI Independent Kin-Type set (verification)mean accuracy: 0.7021 -> 0.6755Hurt
add backpropagation of multiple outputs during joint training (ablation)JLNet · KinfaceWII Independent Kin-Type set (verification)mean accuracy: 0.6190 -> 0.6965Improved
JLNet instead of Multi-class Net on real-scenario retrievalMulti-class Net · KinfaceWI Real-Scenario setF10(all): 0.2947 -> 0.3459Improved

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