FDN: Feature Decoupling Network for Head Pose Estimation

Authors

  • Hao Zhang Institute of Cyber-Systems and Control, Zhejiang University
  • Mengmeng Wang Institute of Cyber-Systems and Control, Zhejiang University
  • Yong Liu Institute of Cyber-Systems and Control, Zhejiang University
  • Yi Yuan NetEase Fuxi AI Lab

DOI:

https://doi.org/10.1609/aaai.v34i07.6974

Abstract

Head pose estimation from RGB images without depth information is a challenging task due to the loss of spatial information as well as large head pose variations in the wild. The performance of existing landmark-free methods remains unsatisfactory as the quality of estimated pose is inferior. In this paper, we propose a novel three-branch network architecture, termed as Feature Decoupling Network (FDN), a more powerful architecture for landmark-free head pose estimation from a single RGB image. In FDN, we first propose a feature decoupling (FD) module to explicitly learn the discriminative features for each pose angle by adaptively recalibrating its channel-wise responses. Besides, we introduce a cross-category center (CCC) loss to constrain the distribution of the latent variable subspaces and thus we can obtain more compact and distinct subspaces. Extensive experiments on both in-the-wild and controlled environment datasets demonstrate that the proposed method outperforms other state-of-the-art methods based on a single RGB image and behaves on par with approaches based on multimodal input resources.

Downloads

Published

2020-04-03

How to Cite

Zhang, H., Wang, M., Liu, Y., & Yuan, Y. (2020). FDN: Feature Decoupling Network for Head Pose Estimation. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 12789-12796. https://doi.org/10.1609/aaai.v34i07.6974

Issue

Section

AAAI Technical Track: Vision