Decoupled multi-task learning with cyclical self-regulation for face parsing
Author(s)
Zheng, Qingping
Deng, Jiankang
Zhu, Zheng
Li, Ying
Zafeiriou, Stefanos
Type
Conference Paper
Abstract
This paper probes intrinsic factors behind typical failure cases (e.g. spatial inconsistency and boundary confusion) produced by the existing state-of-the-art method in face parsing. To tackle these problems, we propose a novel Decoupled Multi-task Learning with Cyclical Self-Regulation (DML-CSR) for face parsing. Specifically, DML-CSR designs a multi-task model which comprises face parsing, binary edge, and category edge detection. These tasks only share low-level encoder weights without high-level interactions between each other, enabling to decouple auxiliary modules from the whole network at the inference stage. To address spatial inconsistency, we develop a dynamic dual graph convolutional network to capture global contextual information without using any extra pooling operation. To handle boundary confusion in both single and multiple face scenarios, we exploit binary and category edge detection to jointly obtain generic geometric structure and fine-grained semantic clues of human faces. Besides, to prevent noisy labels from degrading model generalization during training, cyclical self-regulation is proposed to self-ensemble several model instances to get a new model and the resulting model then is used to self-distill subsequent models, through alternating iterations. Experiments show that our method achieves the new state-of-the-art performance on the Helen, CelebAMask-HQ, and Lapa datasets. The source code is available at https://github.com/deepinsight/insightface/tree/master/parsing/dml_csr.
Date Issued
2022-09-27
Date Acceptance
2022-06-18
Citation
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp.4146-4155
ISSN
1063-6919
Publisher
IEEE Computer Soc.
Start Page
4146
End Page
4155
Journal / Book Title
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Copyright Statement
© 2022 IEEE. This CVPR paper is the Open Access versions, provided by the Computer Vision Foundation. Except for the watermark, they are identical to the accepted versions; the final published version of the proceedings is available on IEEE Xplore.
Source
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Subjects
Computer Science
Computer Science, Artificial Intelligence
Imaging Science & Photographic Technology
Science & Technology
Technology
Publication Status
Published
Start Date
2022-06-18
Finish Date
2022-06-24
Coverage Spatial
LA, New Orleans