Treat noise as domain shift: Noise feature disentanglement for underwater perception and maritime surveys in side-scan sonar images

Y Yu, J Zhao, C Huang, X Zhao - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
In underwater perception and maritime surveys, due to the scarcity of training data and
perturbation of speckle noise, the detection performance of underwater objects in side-scan …

Remove and recover: Two stage convolutional autoencoder based sonar image enhancement algorithm

T Liu, S Yan, G Wang - Multimedia Tools and Applications, 2024 - Springer
High-quality forward-looking sonar images are the basic guarantee for underwater object
detection and classification of autonomous underwater vehicle (AUV). However, the sonar …

SEGSID: A Semantic-Guided Framework for Sonar Image Despeckling

S Liu, J Lu, H Dou, J Li, Y Deng - IEEE Transactions on Image …, 2024 - ieeexplore.ieee.org
Sonar imagery is substantially degraded by speckle noise, making the task of despeckling
crucial for improving image quality. Self-supervised despeckling methods, represented by …

Advancing robust underwater acoustic target recognition through multitask learning and multi-gate mixture of experts

Y **e, J Ren, J Li, J Xu - The Journal of the Acoustical Society of …, 2024 - pubs.aip.org
Underwater acoustic target recognition has emerged as a prominent research area within
the field of underwater acoustics. However, the current availability of authentic underwater …

多级度量网络的小样本学**.

韦世红, 刘红梅, 唐宏, 朱龙娇 - Journal of Computer …, 2023 - search.ebscohost.com
小样本学**的分类结果依赖于模型对样本特征的表达能力, 为了进一步挖掘图像所表达的语义
信息, 提出一种多级度量网络的小样本学**方法. 将输入图像的特征向量放入嵌入模块进行特征 …

基于对比学**方法的小样本学**

付海涛, 刘烁, 冯宇轩, 朱丽, 张竞吉… - 吉林大学学报 (理学版 …, 2023 - xuebao.jlu.edu.cn
针对目前小样本学**中存在的问题, 设计一种新的网络结构及其训练方法以改进小样本学**.
该网络在特征嵌入部分采用卷积网络并结合多尺度滑动池化方法以增**特征提取 …