Fusion Network for Face-based Age Estimation
This work addresses age estimation, a specific computer vision task, with an incremental improvement in accuracy for applications like biometrics or demographic analysis.
The paper tackled age estimation from faces by proposing a Fusion Network (FusionNet) that incorporates age-specific facial patches alongside the whole face image, resulting in significant outperformance over state-of-the-art models on the MORPH II benchmark.
Convolutional Neural Networks (CNN) have been applied to age-related research as the core framework. Although faces are composed of numerous facial attributes, most works with CNNs still consider a face as a typical object and do not pay enough attention to facial regions that carry age-specific feature for this particular task. In this paper, we propose a novel CNN architecture called Fusion Network (FusionNet) to tackle the age estimation problem. Apart from the whole face image, the FusionNet successively takes several age-specific facial patches as part of the input to emphasize the age-specific features. Through experiments, we show that the FusionNet significantly outperforms other state-of-the-art models on the MORPH II benchmark.