Integrating ConvNeXt and Vision Transformers for Enhancing Facial Age Estimation

TL;DR

This paper introduces a hybrid model combining ConvNeXt and Vision Transformers for facial age estimation, achieving superior accuracy on benchmark datasets by leveraging the strengths of both architectures.

Contribution

The study presents a novel ConvNeXt-ViT hybrid architecture that enhances age estimation accuracy through integrated CNN and transformer features, with extensive evaluation and ablation studies.

Findings

Outperforms traditional age estimation methods

Achieves lower mean absolute error on benchmark datasets

Highlights importance of adapted attention mechanisms

Abstract

Age estimation from facial images is a complex and multifaceted challenge in computer vision. In this study, we present a novel hybrid architecture that combines ConvNeXt, a state-of-the-art advancement of convolutional neural networks (CNNs), with Vision Transformers (ViT). While each model independently delivers excellent performance on a variety of tasks, their integration leverages the complementary strengths of the CNNs localized feature extraction capabilities and the Transformers global attention mechanisms. Our proposed ConvNeXt-ViT hybrid solution was thoroughly evaluated on benchmark age estimation datasets, including MORPH II, CACD, and AFAD, and achieved superior performance in terms of mean absolute error (MAE). To address computational constraints, we leverage pre-trained models and systematically explore different configurations, using linear layers and advanced regularization techniques to optimize the architecture. Comprehensive ablation studies highlight the critical role of individual components and training strategies, and in particular emphasize the importance of adapted attention mechanisms within the CNN framework to improve the model focus on age-relevant facial features. The results show that the ConvNeXt-ViT hybrid not only outperforms traditional methods, but also provides a robust foundation for future advances in age estimation and related visual tasks. This work underscores the transformative potential of hybrid architectures and represents a promising direction for the seamless integration of CNNs and transformers to address complex computer vision challenges.