CSGN: Combined Channel- and Spatial-Wise Dynamic Gating Architecture for Convolutional Neural Networks
The explosive computation and memory requirements of convolutional neural networks (CNNs) hinder their deployment in resource-constrained devices. Because conventional CNNs perform identical parallelized computations even on redundant pixels, the saliency of various features in an image should be re...
Main Authors: | Sangmin Hyun, Chang Ho Ryu, Ju Yeon Kang, Hyun Jo Lim, Tae Hee Han |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-08-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/11/17/2678 |
Similar Items
-
Sparse convolutional neural network acceleration with lossless input feature map compression for resource‐constrained systems
by: Jisu Kwon, et al.
Published: (2022-01-01) -
Multi-Channel Bin-Wise Speech Separation Combining Time-Frequency Masking and Beamforming
by: Mostafa Bella, et al.
Published: (2023-01-01) -
MEGS: A Penalty for Mutually Exclusive Group Sparsity
by: Charles Saunders, et al.
Published: (2023-01-01) -
Pushing the Limits of Biosensing: Selective Calcium Ion Detection with High Sensitivity via High-<i>k</i> Gate Dielectric Engineered Si Nanowire Random Network Channel Dual-Gate Field-Effect Transistors
by: Tae-Hwan Hyun, et al.
Published: (2023-07-01) -
Efficient Hardware Design and Implementation of the Voting Scheme-Based Convolution
by: Pedro Pereira, et al.
Published: (2022-04-01)