2D Wasserstein loss for robust facial landmark detection

作者：

Highlights：

• Rethink the problem of robust facial landmark detection between the reaserch and the practical use.

• Novel method based on the Wasserstein loss to significantly improve the robustness of facial landmark detection.

• Several modifications to the current evaluation metrics to reflect the robustness of the state-of-the-art methods more effectively.

摘要

•Rethink the problem of robust facial landmark detection between the reaserch and the practical use.•Novel method based on the Wasserstein loss to significantly improve the robustness of facial landmark detection.•Several modifications to the current evaluation metrics to reflect the robustness of the state-of-the-art methods more effectively.

论文关键词：Facial landmark detection,Face alignment,Heatmap regression,Wasserstein distance

论文评审过程：Received 30 June 2020, Revised 24 February 2021, Accepted 5 March 2021, Available online 13 March 2021, Version of Record 21 March 2021.

论文官网地址：https://doi.org/10.1016/j.patcog.2021.107945