Research map / Label-efficient and robust learning / Recognition and long-tail
Decorrelated Adversarial Learning for Age-Invariant Face Recognition
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 classification supervision without DAL (ablation) | Baseline face recognition model · FG-NET MF1 | rank-1 identification rate: 55.86% -> 55.84% | No clear effect |
| add age classification supervision without DAL (ablation) | Baseline face recognition model · FG-NET MF2 | rank-1 identification rate: 58.85% -> 58.64% | No clear effect |
| add age classification supervision without DAL (ablation) | Baseline face recognition model · MORPH Album 2 | rank-1 identification rate: 98.21% -> 98.11% | No clear effect |
| add age classification supervision without DAL (ablation) | Baseline face recognition model · CACD-VS | verification accuracy: 99.07% -> 99.05% | No clear effect |
| add DAL decorrelation regularization to age- and identity-supervised training (ablation) | Age-supervised face recognition model · FG-NET MF1 | rank-1 identification rate: 55.84% -> 57.92% | Helped |
| add DAL decorrelation regularization to age- and identity-supervised training (ablation) | Age-supervised face recognition model · FG-NET MF2 | rank-1 identification rate: 58.64% -> 60.01% | Helped |
| add DAL decorrelation regularization to age- and identity-supervised training (ablation) | Age-supervised face recognition model · FG-NET leave-one-out | rank-1 identification rate: 93.6% -> 94.5% | Helped |
| add DAL decorrelation regularization to age- and identity-supervised training (ablation) | Age-supervised face recognition model · MORPH Album 2 | rank-1 identification rate: 98.11% -> 98.93% | Helped |
| add DAL decorrelation regularization to age- and identity-supervised training (ablation) | Age-supervised face recognition model · CACD-VS | verification accuracy: 99.05% -> 99.40% | Helped |
| add DAL decorrelation regularization (ablation) | Identity-dependent features · Small training dataset, across age groups | cosine similarity to identity class center | Helped |
Closest papers by meaning
- When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework (CVPR 2021 · similarity 0.90)
- Look across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition (AAAI 2019 · similarity 0.90)
- Latent Factor Guided Convolutional Neural Networks for Age-Invariant Face Recognition (CVPR 2016 · similarity 0.90)
- Face Aging With Identity-Preserved Conditional Generative Adversarial Networks (CVPR 2018 · similarity 0.88)
- From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging (NeurIPS 2025 · similarity 0.85)
- AQUAFace: Age-Invariant Quality Adaptive Face Recognition for Unconstrained Selfie vs ID Verification (AAAI 2025 · similarity 0.83)
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.