Research map / Label-efficient and robust learning / Recognition and long-tail
Look across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Jointly learn age-invariant representations and cross-age face synthesis | AIM · CAFR | Acc (%): 73.56$\pm$1.39 -> 84.81$\pm$0.93 | Helped |
| Add CAFR training data | AIM · MORPH Album2 Setting-1 | Rank-1 recognition rate (%): 99.13 -> 99.65; further improved by 0.52% | Helped |
| Add CAFR training data | AIM · MORPH Album2 Setting-2 | Rank-1 recognition rate (%): 98.81 -> 99.26; further improved by 0.45% | Helped |
| Add CAFR training data | AIM · CACD-VS | Acc (%): 99.38 -> 99.76; further gains 0.38% | Helped |
| Add cross-age domain adversarial training with C_phi (ablation) | AIM · CAFR | Acc (%): 78.85$\pm$1.39 -> 84.81$\pm$0.93 | Helped |
| Add cross-entropy regularization with label smoothing (ablation) | AIM · CAFR | Acc (%): 80.39$\pm$1.19 -> 84.81$\pm$0.93 | Helped |
| Add the attention mechanism (ablation) | AIM · CAFR | Acc (%): 82.25$\pm$1.03 -> 84.81$\pm$0.93 | Helped |
| Add identity-preserving loss L_ip (ablation) | AIM · CAFR | Acc (%): 67.64$\pm$0.88 -> 84.81$\pm$0.93 | Helped |
| Add adversarial loss L_adv1 (ablation) | AIM · CAFR | Acc (%): 81.02$\pm$1.10 -> 84.81$\pm$0.93 | Helped |
| Add age-estimation loss L_ae (ablation) | AIM · CAFR | Acc (%): 81.83$\pm$1.29 -> 84.81$\pm$0.93 | Helped |
| Add manifold-consistency loss L_mc (ablation) | AIM · CAFR | Acc (%): 82.03$\pm$0.98 -> 84.81$\pm$0.93 | Helped |
| Add adversarial loss L_adv2 (ablation) | AIM · CAFR | Acc (%): 82.30$\pm$0.99 -> 84.81$\pm$0.93 | Helped |
Closest papers by meaning
- When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework (CVPR 2021 · 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 0.85)
- 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 0.84)
- Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors (ICLR 2025 · similarity 0.84)
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.