.png){kind=icon}
返回
Continual Learning Approach for Remote Sensing Scene Classification
.png){kind=icon}
PRE
AI
DOI：10.1109/LGRS.2020.3019071.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this letter, we propose a continual learning approach for a set of sequential scene classification tasks, where each task contains a group of land-cover classes. Our aim is to learn new tasks in a continual way without significantly degrading the performances of the old ones, due to the tricky catastrophic forgetting problem inherent to neural networks. To this end, we propose a neural architecture composed of two trainable modules. The first module learns its weights by discriminating between the land-cover classes within the new task while keeping trace of the old ones. On the other side, the second module tries to maximize the separation between the tasks by learning on task-prototypes stored in a linear memory (one prototype per task). The experimental results on two scene data sets (Merced and Optimal31) confirm the promising capability of the proposed method.
Keyword:
Task analysis
Training
Remote sensing
Neural networks
Prototypes
Computer architecture
Central Processing Unit
Catastrophic forgetting
continual learning
remote sensing
scene classification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
16.4
论文数:
1.0W
被引数:
5.1K
机构
引用论文
Lymphokine-activated killer (LAK) cells and cytokines synergize to kill clonal cells in acute myeloid leukemia (AML) in vitro.png)
Haematologia
HaematologiaIF0
PREAI
分享收藏分享收藏AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene ClassificationAID: 用于航空场景分类性能评估的基准数据集
OAAI
OAAI分享收藏
查看更多内容