Neural Network Compression via Low Frequency Preference
Network pruning has been widely used in model compression techniques, and offers a promising prospect for deploying models on devices with limited resources. Nevertheless, existing pruning methods merely consider the importance of feature maps and filters in the spatial domain. In this paper, we re-...
Main Authors: | Chaoyan Zhang, Cheng Li, Baolong Guo, Nannan Liao |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-06-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/15/12/3144 |
Similar Items
-
Neural Network Light Weighting Approach Using Multi-Metric Evaluation of Convolution Kernels
by: Pengyu Wang, et al.
Published: (2023-01-01) -
Channel Pruning Method Based on Decoupling Feature Scale Distribution in Batch Normalization Layers
by: Zijie Qiu, et al.
Published: (2024-01-01) -
A Method of Deep Learning Model Optimization for Image Classification on Edge Device
by: Hyungkeuk Lee, et al.
Published: (2022-09-01) -
Literature Review of Deep Network Compression
by: Ali Alqahtani, et al.
Published: (2021-11-01) -
Deep Neural Network Compression Technique Towards Efficient Digital Signal Modulation Recognition in Edge Device
by: Ya Tu, et al.
Published: (2019-01-01)