Research map / Label-efficient and robust learning / Recognition and long-tail
Latent Factor Guided Convolutional Neural Networks 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 |
|---|---|---|---|
| Use LF-CNNs with latent identity analysis-guided age-invariant features instead of the CNN baseline fine-tuned on MORPH training data | CNN face recognition on MORPH Album 2 · MORPH Album 2 | Rank-1 identification rate: 95.13% -> 97.51% | Helped |
| Use LF-CNNs instead of the CNN baseline | CNN face recognition · FG-NET | Rank-1 identification rate: 84.4% -> 88.1% | Helped |
| Use LF-CNNs instead of the CNN baseline | CNN face recognition · FG-NET, age 0–16 | Rank-1 identification rate: 76.47% -> 81.37% | Helped |
| Use LF-CNNs instead of the CNN baseline | CNN face recognition · FG-NET, age 17–69 | Rank-1 identification rate: 96.93% -> 98.72% | Helped |
| Use LF-CNNs instead of the CNN baseline | CNN face recognition · FG-NET, age 0–4 | Rank-1 identification rate: 51.81% -> 60.10% | Helped |
| Use LF-CNNs instead of the CNN baseline | CNN face recognition · FG-NET, age 5–10 | Rank-1 identification rate: 84.86% -> 88.53% | Helped |
| Use LF-CNNs instead of the CNN baseline | CNN face recognition · FG-NET, age 11–16 | Rank-1 identification rate: 91.04% -> 94.03% | Helped |
| Use LF-CNNs instead of the CNN baseline | CNN face recognition · FG-NET, age 17–24 | Rank-1 identification rate: 94.51% -> 97.80% | Helped |
| Use LF-CNNs instead of the CNN baseline | CNN face recognition · FG-NET, age 25–69 | Rank-1 identification rate: 99.04% -> 99.52% | Helped |
| Use LF-CNNs instead of human voting | Age-invariant face verification · CACD-VS | Accuracy: 94.2% -> 98.5% | Helped |
| Use the 25-network LF-CNN ensemble instead of a single LF-CNN | LF-CNNs · LFW | Accuracy: 99.10% -> 99.50% | Helped |
| Fine-tune the CNN baseline with MORPH training data | CNN-baseline on MORPH Album 2 · MORPH Album 2 | Rank-1 identification rate: 89.68% -> 95.13% | 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 0.91)
- When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework (CVPR 2021 · similarity 0.91)
- Decorrelated Adversarial Learning for Age-Invariant Face Recognition (CVPR 2019 · similarity 0.90)
- Deep Regression Forests for Age Estimation (CVPR 2018 · similarity 0.88)
- Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machines (CVPR 2016 · similarity 0.88)
- From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging (NeurIPS 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.