.png){kind=icon}
返回
Energy-Based CNN Pruning for Remote Sensing Scene Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2023.3277077.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Convolutional neural networks (CNNs) have been adopted to classify the remote sensing scene image. However, the application of these complicated networks on the satellite platform is difficult because of the limited computation resources. Therefore, we propose an energy-based filter pruning framework (EFPF) to reduce the size of the original model. The energy can be obtained through the eigenvalues of each weight tensor by singular value decomposition (SVD). Specifically, we calculate the energy of each layer by the ratio of eigenvalues that are lower than a specified truncation parameter and then remove filters from the original layer in light of the degree of energy. The EFPF is reliable, because SVD techniques can capture the covariance among all filters from the original weight tensor, and therefore, the energy from the eigenvalues can reflect the redundancy of the filters (i.e., if the distribution of eigenvalues is sharp, then the energy among filters will be lower, and the redundancy will be higher). Surprisingly, the EFPF can reduce the floating point operations (FLOPs) and parameters, as well as improve the top1 accuracy obviously when the VGG-16 and ResNet-50 are adopted to classify the AID, NWPU45, PatternNet, and WHU19 datasets. Additionally, the EFPF can achieve similar pruning results when the original model is fully trained (converge) and undertrained (In-converge), which means that we can save the training computation resources for the original model.
Keyword:
Eigenvalues and eigenfunctions
Remote sensing
Computational modeling
Tensors
Redundancy
Satellites
Computer architecture
Convolutional neural network (CNN)
energy-based
filter pruning
remote sensing scene image classification
期刊
IF:
8.6
论文数:
2.2W
被引数:
10.7W
机构
引用论文
.png){kind=icon}
Self-Supervised GlobalLocal Contrastive Learning for Fine-Grained Change Detection in VHR Images
PREAI
分享收藏
A Feature Aggregation Convolutional Neural Network for Remote Sensing Scene Classification用于遥感场景分类的特征聚合卷积神经网络
PREAI
分享收藏
查看更多内容