Deep Learning Face Representation by Joint Identification-Verification

TL;DR

This paper introduces DeepID2, a deep learning-based face recognition method that combines identification and verification signals to learn robust features, achieving state-of-the-art accuracy on LFW with significant error reduction.

Contribution

It presents a novel joint identification-verification deep learning framework for face recognition, improving intra- and inter-personal variation handling.

Findings

Achieved 99.15% face verification accuracy on LFW.

Reduced error rate by 67% compared to previous deep learning methods.

Learned features generalize well to unseen identities.

Abstract

The key challenge of face recognition is to develop effective feature representations for reducing intra-personal variations while enlarging inter-personal differences. In this paper, we show that it can be well solved with deep learning and using both face identification and verification signals as supervision. The Deep IDentification-verification features (DeepID2) are learned with carefully designed deep convolutional networks. The face identification task increases the inter-personal variations by drawing DeepID2 extracted from different identities apart, while the face verification task reduces the intra-personal variations by pulling DeepID2 extracted from the same identity together, both of which are essential to face recognition. The learned DeepID2 features can be well generalized to new identities unseen in the training data. On the challenging LFW dataset, 99.15% face verification accuracy is achieved. Compared with the best deep learning result on LFW, the error rate has been significantly reduced by 67%.