Does Pixel Value Represent Facial Landmark Well in Heatmap?
- 13 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (12) , 13016-13028
Abstract
Heatmap-based methods have dominated the face alignment task, yet the maximum response decoding scheme necessitates further reform. While some studies have attempted to compensate for prediction offsets using a post-processing module, the prediction errors induced by the maximum response decoding scheme remain challenging to rectify. In this paper, we assume that using heatmap value to denote the ground-truth probability is not accurate enough. To cure this problem, we propose DISPAL, a novel DIS tribution-based P robability for f A cial L andmarks, which signifies the ground-truth probability by the similarity between the pixel’s neighbouring value distribution and Gaussian distribution. This innovative probability enables us to pinpoint the keypoint location more robustly than previous methods that rely solely on the peak score. It also exhibits remarkable generalization to complex decoding methodologies. Furthermore, we propose supervising this probability as an additional task loss to help the model learn better heatmap representation. Extensive empirical results on WFLW, 300W, and COFW datasets demonstrate that our distribution-based probability mechanism significantly surpasses original value-based probability approaches.Keywords
Funding Information
- National Natural Science Foundation of China (62236006, 62320106007, 62032022, 62106267)
- Scientific Research Program of Beijing Municipal Education Commission (KZ201911417048)
This publication has 49 references indexed in Scilit:
- Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian2022
- Structured Landmark Detection via Topology-Adapting Deep Graph Learning2020
- Robust Facial Landmark Detection via Recurrent Attentive-Refinement Networks2016
- Stacked Hourglass Networks for Human Pose Estimation2016
- Face alignment by coarse-to-fine shape searching2015
- Collaborative Facial Landmark Localization for Transferring Annotations Across Datasets2014
- Supervised Descent Method and Its Applications to Face Alignment2013
- Face detection, pose estimation, and landmark localization in the wild2012
- Face alignment by Explicit Shape Regression2012
- Interactive Facial Feature Localization2012