Research map / Label-efficient and robust learning / Recognition and long-tail
Disentangled Representation for Age-Invariant Face Recognition: A Mutual Information Minimization Perspective
Xuege Hou, Yali Li, Shengjin Wang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add mutual information minimization between identity and age features (ablation) | MT-MIM (ArcFace baseline) · MORPH Album 2 | Rank-1 accuracy (%): 99.00 -> 99.43 | Improved |
| add mutual information minimization (ablation) | MT-MIM · CACD (2004-2006) | Rank-1 accuracy (%): 91.81 -> 92.63 | Improved |
| add mutual information minimization (ablation) | MT-MIM · CACD (2007-2009) | Rank-1 accuracy (%): 93.27 -> 93.95 | Improved |
| add mutual information minimization (ablation) | MT-MIM · CACD (2010-2012) | Rank-1 accuracy (%): 95.35 -> 96.09 | Improved |
| add mutual information minimization (ablation) | MT-MIM · FG-NET (leave-one-out) | Rank-1 accuracy (%): 93.20 -> 94.21 | Improved |
| add mutual information minimization (ablation) | MT-MIM · FG-NET (MF2) | Rank-1 accuracy (%): 60.26 -> 61.12 | Improved |
| add mutual information minimization (ablation) | MT-MIM · AgeDB-30 | Rank-1 accuracy (%): 95.11 -> 96.10 | Improved |
| add age classification supervision alone (without MI minimization) (ablation) | ArcFace baseline · CACD (2007-2009) | Rank-1 accuracy (%): 93.27 -> 93.15 | No clear effect |
| add age classification supervision alone (ablation) | ArcFace baseline · FG-NET (MF2) | Rank-1 accuracy (%): 60.26 -> 60.04 | No clear effect |
| add age classification supervision alone (ablation) | ArcFace baseline · AgeDB-30 | Rank-1 accuracy (%): 95.11 -> 95.40 | Improved |
| add MI minimization on top of age supervision (ablation) | MT-MIM · MORPH Album 2 | Rank-1 accuracy (%): 99.10 -> 99.43 | Improved |
| fine-tune on CACD after general face pretraining | CNN baseline · CACD (2004-2006) | MAP (%): 68.21 -> 91.81 | Improved |
Closest papers by meaning
- TimeBooth: Disentangled Facial Invariant Representation for Diverse and Personalized Face Aging (ICCV 2025 · similarity 0.93)
- Towards Age-Invariant Face Recognition (TPAMI 2020 · similarity 0.92)
- When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework (CVPR 2021 · similarity 0.92)
- Look across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition (AAAI 2019 · similarity 0.91)
- From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging (NeurIPS 2025 · similarity 0.88)
- AQUAFace: Age-Invariant Quality Adaptive Face Recognition for Unconstrained Selfie vs ID Verification (AAAI 2025 · 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.
