Learning Deep Face Representation

TL;DR

This paper introduces a simple, fast, and efficient deep learning framework called Pyramid CNN for face representation, achieving high accuracy and state-of-the-art performance on benchmark datasets.

Contribution

The paper proposes a novel Pyramid CNN structure that enables fast training, feature sharing across scales, and improved discriminative face representations.

Findings

Achieves 85.8% accuracy on LFW with 8-dimensional features.

Extends to feature-sharing Pyramid CNN with 97.3% accuracy on LFW.

Demonstrates good generalization on social network face images.

Abstract

Face representation is a crucial step of face recognition systems. An optimal face representation should be discriminative, robust, compact, and very easy-to-implement. While numerous hand-crafted and learning-based representations have been proposed, considerable room for improvement is still present. In this paper, we present a very easy-to-implement deep learning framework for face representation. Our method bases on a new structure of deep network (called Pyramid CNN). The proposed Pyramid CNN adopts a greedy-filter-and-down-sample operation, which enables the training procedure to be very fast and computation-efficient. In addition, the structure of Pyramid CNN can naturally incorporate feature sharing across multi-scale face representations, increasing the discriminative ability of resulting representation. Our basic network is capable of achieving high recognition accuracy ($85.8\%$ on LFW benchmark) with only 8 dimension representation. When extended to feature-sharing Pyramid CNN, our system achieves the state-of-the-art performance ($97.3\%$) on LFW benchmark. We also introduce a new benchmark of realistic face images on social network and validate our proposed representation has a good ability of generalization.