Deep learning-based synthetic aperture radar (SAR) target recognition often suffers from sparsely distributed training samples and rapid angular variations due to scattering scintillation. Thus, data-driven SAR is considered a typical few-shot learning (FSL) task. This article first reviews the key issues of FSL provides definition A novel adversarial autoencoder (AAE) then proposed as an repre...

Cavity under urban roads has increasingly become a huge threat to traffic safety. This paper aims study cavity morphology characteristics and proposes deep learning (DL)-based classification method using the 3D ground-penetrating radar (GPR) data. Fine-tuning technology in DL can be used some cases with relatively few samples, but case of only one or very there will still overfitting problems. ...

We propose a framework for assessing the hippocampi on stroke patients and studies of small vessel disease, where sclerosis, perivascular spaces and infarcts on this structure are common. It includes hippocampal and cavity segmentations, hippocampal shape modelling, feature characterisation and statistical analyses, all which have been particularly developed for assessing extreme abnormalities ...

The overall volume of freshwater entering the Arctic Ocean has been growing as glaciers melt and river runoff increases. Since 1980, a 20% increase in observed system. As discharges Ob, Yenisei, Lena rivers are an important source Kara Laptev Seas, discharge might have significant impact on upper ocean circulation. fresh water mixes with forms large freshened surface layer (FSL), which carries ...

In few-shot unsupervised domain adaptation (FS-UDA), most existing methods followed the learning (FSL) to leverage low-level local features (learned from conventional convolutional models, e.g., ResNet) for classification. However, goal of FS-UDA and FSL are relevant yet distinct, since aims classify samples in target rather than source domain. We found that insufficient FS-UDA, which could int...

In cross-domain hyperspectral image (HSI) classification, the labeled samples of target domain are very limited, and it is a worthy attention to obtain sufficient class information from source categorize classes (both same new unseen classes). This article investigates this problem by employing few-shot learning (FSL) in meta-learning paradigm. However, most existing FSL methods extract statist...

Increasing concerns on intelligent spectrum sensing call for efficient training and inference technologies. In this paper, we propose a novel federated learning (FL) framework, dubbed (FSL), which exploits the benefits of reconfigurable surfaces (RISs) overcomes unfavorable impact deep fading channels. Distinguishingly, endow conventional RISs with capabilities by leveraging fully-trained convo...

Recent Few-Shot Learning (FSL) methods put emphasis on generating a discriminative embedding features to precisely measure the similarity between support and query sets. Current CNN-based cross-attention approaches generate representations via enhancing mutually semantic similar regions of pairs. However, it suffers from two problems: CNN structure produces inaccurate attention map based local ...

A Space and Time Mesoscale Analysis System (STMAS) has been developed at Forecast Systems Laboratory (FSL) to generate a gridded analysis of surface observations. It is a three-dimensional variational analysis (3DVAR) of horizontal space and time instead of pressure or height levels. It is used to detect boundary layer phenomena, frontal zones, and various nonlinear phenomena, and has been used...