1 code implementation • 24 Jul 2022 • Zheng Tong, Tao Ma, Ju Huyan, Weiguang Zhang
However, few current public datasets limit the potential exploration of deep learning in the application of pavement damage segmentation.
no code implementations • 23 Aug 2021 • Zheng Tong, Philippe Xu, Thierry Denoeux
We propose an information-fusion approach based on belief functions to combine convolutional neural networks.
1 code implementation • 25 Mar 2021 • Zheng Tong, Philippe Xu, Thierry Denœux
We propose a hybrid architecture composed of a fully convolutional network (FCN) and a Dempster-Shafer layer for image semantic segmentation.
2 code implementations • 25 Mar 2021 • Zheng Tong, Philippe Xu, Thierry Denœux
We propose a new classifier based on Dempster-Shafer (DS) theory and a convolutional neural network (CNN) architecture for set-valued classification.