计算机科学
卷积神经网络
拓扑(电路)
合成孔径雷达
上下文图像分类
网络拓扑
特征提取
人工智能
人工神经网络
特征(语言学)
模式识别(心理学)
算法
图像(数学)
操作系统
哲学
组合数学
语言学
数学
作者
Jihao Li,Martin Weinmann,Xian Sun,Wenhui Diao,Yingchao Feng,Kun Fu
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing
[Institute of Electrical and Electronics Engineers]
日期:2021-08-13
卷期号:60: 1-17
被引量:2
标识
DOI:10.1109/tgrs.2021.3102988
摘要
With the proposal of neural architecture search (NAS), automated network architecture design gradually becomes a new way in deep learning research. Due to its high capability regarding automated design, some pioneers have made an attempt to apply NAS in remote sensing and made some achievements, like 1-D/3-D Auto-convolutional neural network (CNN) and polarimetric synthetic aperture radar (PolSAR)-tailored Differentiable Architecture Search (PDAS). However, there are still some areas to be improved for existing NAS in remote-sensing field. In this article, we propose a random topology and random multiscale mapping (RTRMM) method to generate a multiscale and lightweight architecture for remote-sensing image recognition. First, a random topology generator generates the topology through random graph. Second, during the experiment, we find remote-sensing image features extracted by a multiscale network are more appropriate, compared with features extracted by a single-scale model. Nevertheless, the complexity inevitably increases with the introduction of a multiscale concept. Consequently, we design a variable search space consisting of decomposition convolution units under the guidance of mathematical analysis. The mapping of each neuron is then determined by a random multiscale mapping sampler. After that, we assemble the topology and mappings into blocks and construct three RTRMM models. Experiments on four scene classification datasets confirm the feature extraction capability and lightweight performance of RTRMM models. Moreover, we also observe that our approach achieves a better tradeoff between floating-point operations (FLOPs) and accuracy than some current well-behaved methods. Furthermore, the results on Vaihingen dataset verify the high feature-transfer capability.
科研通智能强力驱动
Strongly Powered by AbleSci AI