DeepID3: Face Recognition with Very Deep Neural Networks

TL;DR

This paper introduces two very deep neural network architectures, DeepID3, for face recognition, achieving state-of-the-art accuracy by adapting VGG and GoogLeNet structures with joint supervision.

Contribution

The paper develops DeepID3 architectures based on VGG and GoogLeNet, incorporating joint supervision for improved face recognition performance.

Findings

Achieved 99.53% face verification accuracy on LFW

Achieved 96.0% face identification accuracy on LFW

Demonstrated effectiveness of very deep networks for face recognition

Abstract

The state-of-the-art of face recognition has been significantly advanced by the emergence of deep learning. Very deep neural networks recently achieved great success on general object recognition because of their superb learning capacity. This motivates us to investigate their effectiveness on face recognition. This paper proposes two very deep neural network architectures, referred to as DeepID3, for face recognition. These two architectures are rebuilt from stacked convolution and inception layers proposed in VGG net and GoogLeNet to make them suitable to face recognition. Joint face identification-verification supervisory signals are added to both intermediate and final feature extraction layers during training. An ensemble of the proposed two architectures achieves 99.53% LFW face verification accuracy and 96.0% LFW rank-1 face identification accuracy, respectively. A further discussion of LFW face verification result is given in the end.