no code implementations • 19 Apr 2022 • Suorong Yang, Weikang Xiao, Mengchen Zhang, Suhan Guo, Jian Zhao, Furao Shen
By improving the quantity and diversity of training data, data augmentation has become an inevitable part of deep learning model training with image data.
no code implementations • 13 Jun 2021 • Hua Yan, Feng Han, Junyi An, Weikang Xiao, Jian Zhao, Furao Shen
The F1 score of SASICMBERT, whose pretrained model is BERT, is 65. 12%, which is 0. 75% higher than that of SASICMg.