Implementation of Lightweight Convolutional Neural Networks via Layer-Wise Differentiable Compression
Convolutional neural networks (CNNs) have achieved significant breakthroughs in various domains, such as natural language processing (NLP), and computer vision. However, performance improvement is often accompanied by large model size and computation costs, which make it not suitable for resource-co...
Main Authors: | Huabin Diao, Yuexing Hao, Shaoyun Xu, Gongyan Li |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-05-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/10/3464 |
Similar Items
-
Sensitivity-Oriented Layer-Wise Acceleration and Compression for Convolutional Neural Network
by: Wei Zhou, et al.
Published: (2019-01-01) -
A Lightweight Convolutional Neural Network Based on Hierarchical-Wise Convolution Fusion for Remote-Sensing Scene Image Classification
by: Cuiping Shi, et al.
Published: (2022-07-01) -
A Layer-Wise Extreme Network Compression for Super Resolution
by: Jiwon Hwang, et al.
Published: (2021-01-01) -
Detection of ADHD Disorder in Children using Layer-wise Relevance Propagation and Convolutional Neural Network: an EEG Analysis
by: Ali Nouri, et al.
Published: (2024-01-01) -
Block-Wise Separable Convolutions: An Alternative Way to Factorize Standard Convolutions
by: Yan-Jen Huang, et al.
Published: (2024-01-01)