atlas

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

Asymmetric Joint Learning for Heterogeneous Face Recognition

AAAI 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 17 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 synthesized image pairs to joint Bayesian training with a symmetric model (ablation)JB+VGG · CUFSFrank-1 accuracy: 98.43% -> 98.56%Helped
use asymmetric joint learning (inter-class from originals only) instead of symmetric joint Bayesian on synthesized-augmented data (ablation)JB+VGG+Synthesis Methods · CUFSFrank-1 accuracy: 98.56% -> 99.61%Helped
use VGG deep features instead of SIFT/HOG/SURF/Gabor (ablation)AJL-HFR · CUFSFrank-1 accuracyHelped
choose a few synthesis methods (RSLCR, MWF, GANs) rather than all eight (ablation)AJL-HFR · CUFSFrank-1 accuracyMixed
set PCA feature dimension to 750 (ablation)AJL-HFR · CUFSFrank-1 accuracyHelped

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