Deep hybrid dilated residual networks for hyperspectral image classification
Sign Up to like & getrecommendations! Published in 2020 at "Neurocomputing"
DOI: 10.1016/j.neucom.2019.11.092
Abstract: Abstract This study presents a new architecture for deep convolution networks, end-to-end hybrid dilated residual networks wherein 3D cube images are input for hyperspectral image (HSI) classification, and this is termed as 3D-2D SSHDR. The… read more here.
Keywords: classification; residual networks; hybrid dilated; dilated residual ... See more keywords
Dilated residual networks with multi-level attention for speaker verification
Sign Up to like & getrecommendations! Published in 2020 at "Neurocomputing"
DOI: 10.1016/j.neucom.2020.06.079
Abstract: Abstract With the development of deep learning techniques, speaker verification (SV) systems based on deep neural network (DNN) achieve competitive performance compared with traditional i-vector-based works. Previous DNN-based SV methods usually employ time-delay neural network,… read more here.
Keywords: residual networks; speaker verification; level attention; dilated residual ... See more keywords
Learning Optical Flow Using Deep Dilated Residual Networks
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Access"
DOI: 10.1109/access.2019.2898988
Abstract: Nowadays, convolutional neural networks achieve remarkable performance on optical flow estimation because of its strong non-linear fitting ability. Most of them adopt the U-Net architecture, which contains an encoder part and a decoder part. In… read more here.
Keywords: learning optical; dilated residual; flow; optical flow ... See more keywords