Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks

TL;DR

This paper introduces a multi-task cascaded deep learning framework for joint face detection and alignment, leveraging a coarse-to-fine approach and an online hard sample mining strategy to improve accuracy and efficiency in unconstrained environments.

Contribution

The paper proposes a novel multi-task cascaded network with a hard sample mining strategy that jointly improves face detection and alignment performance in challenging conditions.

Findings

Achieves superior accuracy on FDDB, WIDER FACE, and AFLW benchmarks.

Maintains real-time performance while improving detection and alignment.

Outperforms state-of-the-art methods in unconstrained environments.

Abstract

Face detection and alignment in unconstrained environment are challenging due to various poses, illuminations and occlusions. Recent studies show that deep learning approaches can achieve impressive performance on these two tasks. In this paper, we propose a deep cascaded multi-task framework which exploits the inherent correlation between them to boost up their performance. In particular, our framework adopts a cascaded structure with three stages of carefully designed deep convolutional networks that predict face and landmark location in a coarse-to-fine manner. In addition, in the learning process, we propose a new online hard sample mining strategy that can improve the performance automatically without manual sample selection. Our method achieves superior accuracy over the state-of-the-art techniques on the challenging FDDB and WIDER FACE benchmark for face detection, and AFLW benchmark for face alignment, while keeps real time performance.