MobileAgeNet: Lightweight Facial Age Estimation for Mobile Deployment
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916070274629632 |
|---|---|
| author | Kumar, Arun Baiju, Aswathy Timofte, Radu Ignatov, Dmitry |
| author_facet | Kumar, Arun Baiju, Aswathy Timofte, Radu Ignatov, Dmitry |
| contents | Mobile deployment of facial age estimation requires models that balance predictive accuracy with low latency and compact size. In this work, we present MobileAgeNet, a lightweight age-regression framework that achieves an MAE of 4.65 years on the UTKFace held-out test set while maintaining efficient on-device inference with an average latency of 14.4 ms measured using the AI Benchmark application. The model is built on a pretrained MobileNetV3-Large backbone combined with a compact regression head, enabling real-time prediction on mobile devices. The training and evaluation pipeline is integrated into the NN LEMUR Dataset framework, supporting reproducible experimentation, structured hyperparameter optimization, and consistent evaluation. We employ bounded age regression together with a two-stage fine-tuning strategy to improve training stability and generalization. Experimental results show that MobileAgeNet achieves competitive accuracy with 3.23M parameters, and that the deployment pipeline from PyTorch training through ONNX export to TensorFlow Lite conversion - preserves predictive behavior without measurable degradation under practical on-device conditions. Overall, this work provides a practical, deployment-ready baseline for mobile-oriented facial age estimation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17007 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MobileAgeNet: Lightweight Facial Age Estimation for Mobile Deployment Kumar, Arun Baiju, Aswathy Timofte, Radu Ignatov, Dmitry Computer Vision and Pattern Recognition Artificial Intelligence Mobile deployment of facial age estimation requires models that balance predictive accuracy with low latency and compact size. In this work, we present MobileAgeNet, a lightweight age-regression framework that achieves an MAE of 4.65 years on the UTKFace held-out test set while maintaining efficient on-device inference with an average latency of 14.4 ms measured using the AI Benchmark application. The model is built on a pretrained MobileNetV3-Large backbone combined with a compact regression head, enabling real-time prediction on mobile devices. The training and evaluation pipeline is integrated into the NN LEMUR Dataset framework, supporting reproducible experimentation, structured hyperparameter optimization, and consistent evaluation. We employ bounded age regression together with a two-stage fine-tuning strategy to improve training stability and generalization. Experimental results show that MobileAgeNet achieves competitive accuracy with 3.23M parameters, and that the deployment pipeline from PyTorch training through ONNX export to TensorFlow Lite conversion - preserves predictive behavior without measurable degradation under practical on-device conditions. Overall, this work provides a practical, deployment-ready baseline for mobile-oriented facial age estimation. |
| title | MobileAgeNet: Lightweight Facial Age Estimation for Mobile Deployment |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.17007 |