no code implementations • 28 Apr 2022 • Jianrong Zhang, Tianyi Wu, Chuanghao Ding, Hongwei Zhao, Guodong Guo
Specifically, we first propose a Region Mask Contrastive (RMC) loss and a Region Feature Contrastive (RFC) loss to accomplish region-level contrastive property.
no code implementations • 11 Jun 2020 • Hongwei Zhao, Chengtao Peng, Lei Liu, Bin Li
To further prove the generalization property of the proposed method, we applied the trained model on the DRIONS-DB dataset for OD segmentation and on the MESSIDOR dataset for exudate segmentation.
no code implementations • Remote Sensing (ISSN: 2072-4292), MDPI 2019 • Hongwei Zhao, Zhongxin Chen, Hao Jiang, Wenlong Jing, Liang Sun, Min Feng 6
First, we trained 1D CNNs, LSTM RNNs, and GRU RNNs based on the full images’ time series to attain three classifiers with optimal architectures and hyper-parameters.
no code implementations • 14 May 2019 • Xingqian Li, Chenwei Lou, Jian Zhao, HuaPeng Wei, Hongwei Zhao
The consequent urban autism problem has become more and more serious.