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
Check 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 changed | Where | Measured | Effect |
|---|---|---|---|
| add age-estimation supervision to the CosFace baseline (ablation) | MTLFace AIFR · AgeDB-30 | accuracy: 95.52 -> 95.32 | Hurt |
| add age-estimation supervision to the CosFace baseline (ablation) | MTLFace AIFR · CACD-VS | accuracy: 99.12 -> 99.15 | No clear effect |
| add attention-based feature decomposition (ablation) | MTLFace AIFR · cross-age benchmarks | recognition accuracy / Rank-1: 95.52 -> 95.90; 93.64 -> 94.58 | Helped |
| use parallel channel and spatial attention in AFD rather than the single-level CA or SA variants (ablation) | MTLFace AIFR · AgeDB-30 | accuracy: 95.63 -> 95.90; 95.85 -> 95.90 | Mixed |
| add cross-age domain adversarial training to AFD (ablation) | MTLFace AIFR · FG-NET leave-one-out | Rank-1: 94.58 -> 94.78 | Helped |
| add identity conditional module (ICM) for identity-level age synthesis (ablation) | MTLFace FAS · MORPH | Age Acc. (%): 50.80 -> 57.40 | Helped |
| add identity conditional module (ICM) for identity-level age synthesis (ablation) | MTLFace FAS · MORPH | Cos. Sim.: 0.729 -> 0.745 | Helped |
| add identity conditional module (ICM) for identity-level age synthesis (ablation) | MTLFace FAS · FG-NET | Age Acc. (%): 55.26 -> 61.47 | Helped |
| add identity conditional module (ICM) for identity-level age synthesis (ablation) | MTLFace FAS · FG-NET | Cos. Sim.: 0.600 -> 0.638 | Helped |
| add identity conditional module (ICM) for identity-level age synthesis (ablation) | MTLFace FAS · CACD | Age Acc. (%): 55.79 -> 60.62 | Helped |
| add identity conditional module (ICM) for identity-level age synthesis (ablation) | MTLFace FAS · CACD | Cos. Sim.: 0.652 -> 0.676 | Helped |
Closest papers by meaning
- Look across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition (AAAI 2019 · similarity 0.93)
- Latent Factor Guided Convolutional Neural Networks for Age-Invariant Face Recognition (CVPR 2016 · similarity 0.91)
- From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging (NeurIPS 2025 · similarity 0.90)
- AQUAFace: Age-Invariant Quality Adaptive Face Recognition for Unconstrained Selfie vs ID Verification (AAAI 2025 · similarity 0.87)
- Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors (ICLR 2025 · similarity 0.85)
- A Call to Reflect on Evaluation Practices for Age Estimation: Comparative Analysis of the State-of-the-Art and a Unified Benchmark (CVPR 2024 · similarity 0.85)
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.