Large age-gap face verification by feature injection in deep networks

TL;DR

This paper presents a deep learning approach with feature injection for face verification across large age gaps, introducing a new dataset and outperforming existing methods.

Contribution

It proposes a novel feature injection layer in a fine-tuned Siamese DCNN for large age-gap face verification and introduces the LAG dataset.

Findings

Outperforms state-of-the-art face verification methods on LAG dataset

Demonstrates effectiveness of feature injection in deep networks for age-gap verification

Shows that fine-tuning on a large age-gap dataset improves accuracy

Abstract

This paper introduces a new method for face verification across large age gaps and also a dataset containing variations of age in the wild, the Large Age-Gap (LAG) dataset, with images ranging from child/young to adult/old. The proposed method exploits a deep convolutional neural network (DCNN) pre-trained for the face recognition task on a large dataset and then fine-tuned for the large age-gap face verification task. Finetuning is performed in a Siamese architecture using a contrastive loss function. A feature injection layer is introduced to boost verification accuracy, showing the ability of the DCNN to learn a similarity metric leveraging external features. Experimental results on the LAG dataset show that our method is able to outperform the face verification solutions in the state of the art considered.