AI Paper Atlas

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

Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach

Hu Han, Anil K. Jain, Wang Sheng Fang, Shiguang Shan, Xilin Chen

TPAMI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 288 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
train on LFW+ and test on MORPH II instead of same-database training (gender) (ablation)DMTL · MORPH IIgender accuracy (%): 98.0 -> 89.0Hurt
train on MORPH II and test on LFW+ instead of same-database training (race) (ablation)DMTL · LFW+race accuracy (%): 94.9 -> 70.5Hurt
cross-database training on LFWA, test on CelebA (ablation)DMTL · CelebA (40 attributes)average accuracy (%): 93.0 -> 70.2Hurt
cross-database training on CelebA, test on LFWA (ablation)DMTL · LFWA (40 attributes)average accuracy (%): 86.0 -> 73.0Hurt
swap AlexNet shared network for GoogLeNet (ablation)DMTL · CelebA (40 attributes)average accuracy (%): 91.98% -> 92.05%No clear effect
joint multi-task learning instead of single-task AlexNet per attribute (ablation)DMTL · CelebA (eight attributes)attribute accuracyImproved
pre-train on IMDB-WIKI before fine-tuning on LAPAge2015 (ablation)DMTL · LAPAge2015epsilon-error: 0.449 -> 0.289Improved
combine LFW+ age and race with LFWA attributes (LFWA+, different annotation sources) (ablation)DMTL · LFWA+ (42 attributes)average accuracy of 40 attributes (%): 86.0 -> 83Hurt
category-specific subnetworks with shared features instead of multi-label regression with same features (Guo and Mu, Yi et al.)DMTL · MORPH IIage MAE (years): 3.92 -> 3.0 and 3.63 -> 3.0Improved
AlexNet-size multi-task network versus very deep VGG-16 DEX for ageDMTL · MORPH IIage MAE (years): 3.25 -> 3.0Improved
joint estimation on small LFWA training set vs MCNN-AUXDMTL · LFWA (40 attributes)average accuracy (%): 86.0 vs 86.0No clear effect

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