远程传感图像场景分类在混合古典-量子转移CNN与小样本的CNN.
Zhouwei Zhang1,2, Xiaofei Mi1,2, Jian Yang1,2
1Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China.
Sensors (Basel, Switzerland)
|September 28, 2023
概括
这项研究引入了一种混合经典-量子CNN用于遥感图像分类的混合经典-量子CNN,在有限的数据中显著提高了精度. 这种新的方法提高了性能,并减少了与传统方法相比的计算需求.
科学领域:
- 计算机科学 计算机科学
- 量子计算是一种量子计算.
- 遥感 遥感 遥感 遥感
背景情况:
- 深度学习,特别是卷积神经网络 (CNN),在远程传感图像场景分类 (RSISC) 中表现出色.
- 训练CNN通常需要大量的注释数据,这在RSISC中通常很少.
- 在自然图像数据集上预先训练的CNN是一种常见的解决方案,但由于不同的成像机制,远程传感数据可能会出现问题.
研究的目的:
- 提出和评估一个改进的混合经典-量子转移学习CNN的RSISC.
- 为了应对遥感图像分析中有限的注释数据的挑战.
- 为了提高分类准确性,同时减少模型复杂性和数据要求.
主要方法:
- 开发了一种混合CNN模型,集成了经典的ResNet用于特征提取和量子张量电路用于改进.
- 员工通过在近期量子处理器上调参数来转移学习.
- 在一个开源远程传感图像数据集上测试了混合模型.
主要成果:
- 混合古典量子CNN与现有的预训练CNN的RSISC方法相比,表现优越,特别是在小型训练数据集的情况下.
- 实现了更好的分类准确性.
- 显著减少了模型参数的数量和所需的总培训数据.
结论:
- 拟议的混合经典-量子CNN是RSISC的一个有效方法,特别是在处理有限的注释数据时.
- 这种方法为通过量子计算的整合推进远程传感图像分析提供了一个有希望的方向.
- 混合模型为RSISC提供了比传统深度学习技术更有效,更准确的解决方案.
相关概念视频
01:30Classification of Signals
505
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
505
01:26Classification of Systems-I
203
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
203