Balanced Alignment for Face Recognition: A Joint Learning Approach

2020-03-23 · Huawei Wei, Peng Lu, Yichen Wei

Face alignment is crucial for face recognition and has been widely adopted. However, current practice is too simple and under-explored. There lacks an understanding of how important face alignment is and how it should be performed, for recognition. This work studies these problems and makes two contributions. First, it provides an in-depth and quantitative study of how alignment strength affects recognition accuracy. Our results show that excessive alignment is harmful and an optimal balanced point of alignment is in need. To strike the balance, our second contribution is a novel joint learning approach where alignment learning is controllable with respect to its strength and driven by recognition. Our proposed method is validated by comprehensive experiments on several benchmarks, especially the challenging ones with large pose.

📄 PDF Abstract BibTeX arXiv:2003.10168

Code (0)

등록된 구현이 없습니다.

Tasks

Face Alignment Face Recognition

Balanced Masked and Standard Face Recognition

2021-10-04 · Delong Qi, Kangli Hu, Weijun Tan, Qi Yao 외

We present the improved network architecture, data augmentation, and training strategies for the Webface track and Insightface/Glint360K track of the masked face recognition challenge of ICCV2021. One of the key goals is…

Data Augmentation Face Detection Face Recognition

Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition

2017-08-09 · Feng Liu, Qijun Zhao, Xiaoming Liu, Dan Zeng

Face alignment and 3D face reconstruction are traditionally accomplished as separated tasks. By exploring the strong correlation between 2D landmarks and 3D shapes, in contrast, we propose a joint face alignment and 3D f…

3D Face Reconstruction Face Alignment Face Recognition Face Reconstruction

HAA4D: Few-Shot Human Atomic Action Recognition via 3D Spatio-Temporal Skeletal Alignment

2022-02-15 · Mu-Ruei Tseng, Abhishek Gupta, Chi-Keung Tang, Yu-Wing Tai

Human actions involve complex pose variations and their 2D projections can be highly ambiguous. Thus 3D spatio-temporal or 4D (i.e., 3D+T) human skeletons, which are photometric and viewpoint invariant, are an excellent …

Action Recognition Atomic action recognition

Learning to Learn across Diverse Data Biases in Deep Face Recognition

2021-09-29 · CVPR 2022 1 · Chang Liu, Xiang Yu, Yi-Hsuan Tsai, Ramin Moslemi 외

Convolutional Neural Networks have achieved remarkable success in face recognition, in part due to the abundant availability of data. However, the data used for training CNNs is often imbalanced. Prior works largely focu…

Face Recognition Meta-Learning

Recursive Spatial Transformer (ReST) for Alignment-Free Face Recognition

2017-10-01 · ICCV 2017 10 · Wanglong Wu, Meina Kan, Xin Liu, Yi Yang 외

Convolutional Neural Network (CNN) has led to significant progress in face recognition. Currently most CNN-based face recognition methods follow a two-step pipeline, i.e. a detected face is first aligned to a canonical o…