Can I read ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) on EtoBox?

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) by Lv, Yalei (author);Dai, Tao (author);Chen, Bin (author);Lu, Jian (author);Xia, Shu-Tao (author);Cao, Jingchao (author) is a nonfiction available to read on EtoBox.

What is ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) about?

Convolutional neural networks (CNNs) have obtained great success in single image super-resolution (SR). More recent works (e.g., RCAN and SAN) have obtained remarkable performance with channel attention based on first-or second-order statistics of features. However, these methods neglect the rich feature statistics higher than second-order, thus hindering the representation ability of CNNs. To address this issue, we propose a higher-order channel attention (HOCA) module to enhance the representation ability of CNNs. In our HOCA module, to capture different types of semantic information, we first compute k-order of feature statistics, followed by channel attention to learn the feature interdependencies. Considering the diversity of input contents, we design a gate mechanism to adaptively select a specific k-order channel attention. Besides, our HOCA module serves as a plug-and-play module and can be easily plugged into existing state-of-art CNN-based SR methods. Extensive experiments on public benchmarks show that our HOCA module effectively improves the performance of various CNN-based SR methods.

Who reads ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)?

Author

Lv, Yalei (author);Dai, Tao (author);Chen, Bin (author);Lu, Jian (author);Xia, Shu-Tao (author);Cao, Jingchao (author)

Publisher

IEEE

Published

2021

Language

EN

Category

nonfiction