返回
Optimizing the Hyperparameters of Fully Convolutional Encoder-Decoder Networks for SAR Image Segmentation
DOI:10.1109/LGRS.2024.3431216.png)
摘要
En 中文
Fully convolutional encoder-decoder networks have been developed for the segmentation of sensing synthetic aperture radar (SAR) images. A recent one called the multiscaled attention U-net with dilated convolution and offset convolution (MDOAU-net) has been proposed for SAR image segmentation in aquaculture raft monitoring. Despite its excellent performance, its hyperparameters have to be handcrafted based on human experience, consuming a significant amount of time to tune. In this letter, a swarm intelligence algorithm is leveraged to optimize the hyperparameters of fully convolutional encoder-decoder networks (particularly MDOAU-net), including their kernel size, dilation rate, learning rate, batch size, and activation function indicator. Based on segmentation performance, early-stop termination criteria are introduced into a particle swarm optimization (PSO) algorithm to avoid overusing computing resources to train the networks. Specifically, the hyperparameters are optimized using the PSO algorithm with early-stop termination criteria. Experimental results show that the segmentation accuracy of the proposed method reaches 91.49%, which statistically outperforms other methods.
Keyword:
Fully convolutional encoder-decoder network
MDOAU-net
particle swarm optimization (PSO)
synthetic aperture radar (SAR) image segmentation
Fully convolutional encoder-decoder network
MDOAU-net
particle swarm optimization (PSO)
synthetic aperture radar (SAR) image segmentation
期刊
IF:
16.4
论文数:
1.0W
被引数:
5.1K
机构
引用论文
Electrochemically assisted micro localized grafting of aptamers in a microchannel engraved in fluorinated thermoplastic polymer Dyneon THV
RSC Advances
IF0
Accurate Extraction of Mountain Grassland From Remote Sensing Image Using a Capsule Network基于胶囊网络的山地草地遥感影像精确提取
Candidate .gamma.-Secretases in the Generation of the Carboxyl Terminus of the Alzheimer's Disease .beta.A4 Amyloid: Possible Involvement of Cathepsin D候选人。Γ-分泌酶在阿尔茨海默氏病羧基末端的产生。Β.A4淀粉样蛋白: 组织蛋白酶D可能参与
Biochemistry
IF0
Sublook2Sublook: A Self-Supervised Speckle Filtering Framework for Single SAR ImagesSublook2Sublook: 一种用于单幅SAR图像的自监督斑点滤波框架
An Updated Review of the Antimicrobial Potential of Selenium Nanoparticles and Selenium-Related Toxicological Issues硒纳米粒子的抗菌潜力及其相关的毒理学问题研究进展
An improved artificial neural network based on human-behaviour particle swarm optimization and cellular automata基于人类行为粒子群优化和元胞自动机的改进人工神经网络

