# MobileAgeNet: Lightweight Facial Age Estimation for Mobile Deployment

Source: [MobileAgeNet: Lightweight Facial Age Estimation for Mobile Deployment](<https://www.sota2.com/research/paper/69e704c07d0172140ec7eec8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-02T05:02:08.515Z

Authors: Arun Kumar, Aswathy Baiju, Radu Timofte, Dmitry Ignatov

Published: 2026-04-18T14:37:23.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Age Estimation on UTKFace](<https://www.sota2.com/research/sota/age-estimation-on-utkface.md>): Age Estimation; UTKFace; MAE: 4.65.

- [Age Estimation on UTKFace (21-60 years old)](<https://www.sota2.com/research/sota/age-estimation-on-utkface-21-60-years-old.md>): Age Estimation; UTKFace 21-60 years old; MAE: not recorded.

- [Age Estimation on UTKFace Unified benchmark CVPR’24 protocol](<https://www.sota2.com/research/sota/age-estimation-on-utkface-unified-benchmark-cvpr-24-protocol.md>): Age Estimation; UTKFace Unified benchmark CVPR’24 protocol; MAE: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.17007>)

[PDF](<https://arxiv.org/pdf/2604.17007.pdf>)