Order Regularization on Ordinal Loss for Head Pose, Age and Gaze Estimation

Authors

  • Tianchu Guo Artificial Intelligence Center, DAMO Academy, Alibaba Group, Hangzhou, China
  • Hui Zhang Samsung Research China - Beijing (SRC-B)
  • ByungIn Yoo Samsung Advanced Institute of Technology (SAIT), South Korea
  • Yongchao Liu Beijing ByteDance Technology Co., Ltd.
  • Youngjun Kwak Samsung Advanced Institute of Technology (SAIT), South Korea
  • Jae-Joon Han Samsung Advanced Institute of Technology (SAIT), South Korea

Keywords:

Biometrics, Face, Gesture & Pose

Abstract

Ordinal loss is widely used in solving regression problems with deep learning technologies. Its basic idea is to convert regression to classification while preserving the natural order. However, the order constraint is enforced only by ordinal label implicitly, leading to the real output values not strictly in order. It causes the network to learn separable feature rather than discriminative feature, and possibly overfit on training set. In this paper, we propose order regularization on ordinal loss, which makes the outputs in order by explicitly constraining the ordinal classifiers in order. The proposed method contains two parts, i.e. similar-weights constraint, which reduces the ineffective space between classifiers, and differential-bias constraint, which enforces the decision planes in order and enhances the discrimination power of the classifiers. Experimental results show that our proposed method boosts the performance of original ordinal loss on various regression problems such as head pose, age, and gaze estimation, with significant error reduction of around 5%. Furthermore, our method outperforms the state of the art on all these tasks, with the performance gain of 14.4%, 2.2% and 6.5% on head pose, age and gaze estimation respectively.

Downloads

Published

2021-05-18

How to Cite

Guo, T., Zhang, H., Yoo, B., Liu, Y., Kwak, Y., & Han, J.-J. (2021). Order Regularization on Ordinal Loss for Head Pose, Age and Gaze Estimation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1496-1504. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16240

Issue

Section

AAAI Technical Track on Computer Vision I