Deep Multi-Center Learning for Face Alignment

TL;DR

This paper introduces a multi-center deep learning framework for face alignment that uses multiple shape prediction layers focusing on different landmark clusters, improving accuracy and efficiency especially under occlusions.

Contribution

The proposed Multi-Center Learning framework with multiple shape prediction layers and a model assembling method is novel for face alignment, enhancing robustness and reducing model complexity.

Findings

Effective in handling occlusions and appearance variations

Achieves real-time performance

Outperforms existing methods on benchmark datasets

Abstract

Facial landmarks are highly correlated with each other since a certain landmark can be estimated by its neighboring landmarks. Most of the existing deep learning methods only use one fully-connected layer called shape prediction layer to estimate the locations of facial landmarks. In this paper, we propose a novel deep learning framework named Multi-Center Learning with multiple shape prediction layers for face alignment. In particular, each shape prediction layer emphasizes on the detection of a certain cluster of semantically relevant landmarks respectively. Challenging landmarks are focused firstly, and each cluster of landmarks is further optimized respectively. Moreover, to reduce the model complexity, we propose a model assembling method to integrate multiple shape prediction layers into one shape prediction layer. Extensive experiments demonstrate that our method is effective for handling complex occlusions and appearance variations with real-time performance. The code for our method is available at https://github.com/ZhiwenShao/MCNet-Extension.