MobileAgeNet: Lightweight Facial Age Estimation for Mobile Deployment

2026-04-18

AI Summary

This work addresses the challenge of achieving high accuracy, low latency, and model compactness in mobile-based facial age estimation by proposing a lightweight architecture built upon a MobileNetV3-Large backbone coupled with a compact regression head. To enhance prediction accuracy, the method incorporates bounded age regression and a two-stage fine-tuning strategy. The study presents a complete end-to-end pipeline—from PyTorch training and ONNX export to TensorFlow Lite deployment—and demonstrates that the model conversion incurs no performance degradation. Evaluated on the UTKFace test set, the model achieves a mean absolute error (MAE) of 4.65 years with only 3.23 million parameters and an average on-device inference latency of 14.4 milliseconds, effectively balancing efficiency and practicality for real-world mobile applications.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Large Vision Models
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

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.

Problem

• facial age estimation
• mobile deployment
• lightweight model
• low latency
• compact size

Innovation

• lightweight age estimation
• mobile deployment
• bounded regression
• two-stage fine-tuning
• ONNX-to-TFLite pipeline