Memory‐ and time‐efficient dense network for single‐image super‐resolution
Abstract Dense connections in convolutional neural networks (CNNs), which connect each layer to every other layer, can compensate for mid/high‐frequency information loss and further enhance high‐frequency signals. However, dense CNNs suffer from high memory usage due to the accumulation of concatena...
Main Authors: | Nasrin Imanpour, Ahmad R. Naghsh‐Nilchi, Amirhassan Monadjemi, Hossein Karshenas, Kamal Nasrollahi, Thomas B. Moeslund |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2021-04-01
|
Series: | IET Signal Processing |
Online Access: | https://doi.org/10.1049/sil2.12020 |
Similar Items
-
Towards efficient texture classification and abnormality detection
by: Monadjemi, Amirhassan
Published: (2005) -
Deep Residual Dense Network for Single Image Super-Resolution
by: Yogendra Rao Musunuri, et al.
Published: (2021-02-01) -
Multi-Resolution Space-Attended Residual Dense Network for Single Image Super-Resolution
by: Jiayv Qin, et al.
Published: (2020-01-01) -
Robust Real-Time Gradient-based Eye Detection and Tracking Using Transform Domain and PSO-Based Feature Selection
by: Nasrin Salehi, et al.
Published: (2017-07-01) -
Multi-Scale Residual Hierarchical Dense Networks for Single Image Super-Resolution
by: Chuangchuang Liu, et al.
Published: (2019-01-01)