Author: Qi, Delong; Hu, Kangli; Tan, Weijun; Yao, Qi; Liu, Jingfeng
Title: Balanced Masked and Standard Face Recognition Cord-id: 1ge4yyyc Document date: 2021_10_4
ID: 1ge4yyyc
Snippet: 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 to have a balanced performance of masked and standard face recognition. In order to prevent the overfitting for the masked face recognition, we control the total number of masked faces by not more than 10\% of the total face recognition in the training dataset. We propose a few
Document: 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 to have a balanced performance of masked and standard face recognition. In order to prevent the overfitting for the masked face recognition, we control the total number of masked faces by not more than 10\% of the total face recognition in the training dataset. We propose a few key changes to the face recognition network including a new stem unit, drop block, face detection and alignment using YOLO5Face, feature concatenation, a cycle cosine learning rate, etc. With this strategy, we achieve good and balanced performance for both masked and standard face recognition.
Search related documents:
Co phrase search for related documents- accuracy improve and low quality: 1, 2, 3, 4, 5, 6, 7
- accuracy improve and low quality image: 1, 2
- accuracy increase and loss function: 1, 2
- accuracy increase and low quality: 1
- activation unit and loss function: 1, 2, 3
- loss function and low quality: 1, 2, 3, 4, 5
Co phrase search for related documents, hyperlinks ordered by date