.png){kind=icon}
.png){kind=icon}
Return
A Multiscale Incremental Learning Network for Remote Sensing Scene Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2024.3353737.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
To infer unknown remote sensing scenarios, for remote sensing scene classification (RSSC), most existing deep neural networks (DNNs) are trained on closed datasets. When the acquisition speed and quantity of remote sensing images increase rapidly, these models cannot be used to classify new scenes. Currently, incremental learning as an effective solution for solving the catastrophic forgetting issue, but ignoring the stability-plasticity dilemma. In this article, we propose a new incremental learning network, named efficient channel attention-based multiscale depthwise network (ECA-MSDWNet), in which efficient channel attention (ECA) improves the model's ability to focus on critical information in complex context, and multiscale depthwise convolution (MSDW Conv) extracts multiscale features in a fine-grained way. In addition, in incremental learning process, we expand new modules based on a dynamic-structure method to fit the residuals between the labels and the outputs of the old model, enhancing the plasticity of the new model for new tasks while maintaining the performance of the old tasks. Finally, we compress the model to reduce redundant parameters and feature dimensions through an effective knowledge distillation strategy. Experiments on four open datasets demonstrate the effectiveness of our method. Our code is available at https://github.com/zhangyu-chd/ECA-MSDWNet.
Keywords:
Task analysis
Remote sensing
Feature extraction
Data models
Knowledge engineering
Context modeling
Computational modeling
Catastrophic forgetting
incremental learning
multiscale feature
remote sensing scene classification (RSSC)
Journal
IF:
8.6
Papers:
2.1W
Citations:
10.7W