A Deep Face Identification Network Enhanced by Facial Attributes Prediction

TL;DR

This paper introduces a deep learning framework that predicts facial attributes and uses this information to enhance face identification accuracy, demonstrating improved performance over existing methods.

Contribution

The novel end-to-end model fuses predicted facial attributes with face features, outperforming prior multi-task approaches in face recognition and attribute prediction.

Findings

Improved face identification accuracy on standard datasets.

Enhanced facial attribute prediction, especially for identity-related attributes.

Outperforms most existing face recognition and attribute prediction methods.

Abstract

In this paper, we propose a new deep framework which predicts facial attributes and leverage it as a soft modality to improve face identification performance. Our model is an end to end framework which consists of a convolutional neural network (CNN) whose output is fanned out into two separate branches; the first branch predicts facial attributes while the second branch identifies face images. Contrary to the existing multi-task methods which only use a shared CNN feature space to train these two tasks jointly, we fuse the predicted attributes with the features from the face modality in order to improve the face identification performance. Experimental results show that our model brings benefits to both face identification as well as facial attribute prediction performance, especially in the case of identity facial attributes such as gender prediction. We tested our model on two standard datasets annotated by identities and face attributes. Experimental results indicate that the proposed model outperforms most of the current existing face identification and attribute prediction methods.