AI Paper Atlas

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

When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework and a New Benchmark

Zhizhong Huang, Junping Zhang, Hongming Shan

TPAMI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Fair and quality-aware face recognition · 70 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 age estimation loss (ablation)CosFace baseline · AgeDB-30accuracy (%): 95.52 -> 95.32No clear effect
add attention-based feature decomposition (AFD) (ablation)CosFace baseline · AgeDB-30accuracy (%): 95.52 -> 95.90Improved
add AFD (ablation)CosFace baseline · FG-NETrank-1 (%): 93.64 -> 94.58Improved
parallel channel+spatial attention in AFD instead of CBAM (ablation)AFD · AgeDB-30accuracy (%): 96.08 -> 95.90Mixed
add cross-age domain adversarial training (ablation)MTLFace (AFD) · AgeDB-30accuracy (%): 95.90 -> 96.23Improved
fine-tune on all synthesized child faces (FT-All) (ablation)MTLFace w/o FT · AgeDB-30accuracy (%): 96.23 -> 95.88Hurt
fine-tune on selected synthesized faces (FT-Sel) (ablation)MTLFace w/o FT · AgeDB-30accuracy (%): 96.23 -> 96.45Improved
fine-tune on selected synthesized faces (FT-Sel) (ablation)MTLFace w/o FT · FG-NETrank-1 (%): 94.78 -> 95.00Improved
add AIFR task to face age synthesis (ablation)MTLFace · MORPHage accuracy (%): 51.79 -> 67.07Improved
add AIFR task to face age synthesis (ablation)MTLFace · MORPHidentity cosine similarity: 0.219 -> 0.652Improved
add multi-level ICMs (ablation)MTLFace · MORPHage accuracy (%): 64.80 -> 67.07Improved
add ICM (ablation)MTLFace · ECAFMAE: 3.16 -> 2.28Improved

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