Results 31 to 40 of about 116,076 (264)

Semantic-Layout-Guided Image Synthesis for High-Quality Synthetic-Aperature Radar Detection Sample Generation

Remote Sensing, 2023
With the widespread application and functional complexity of deep neural networks (DNNs), the demand for training samples is increasing. This elevated requirement also extends to DNN-based SAR object detection.
Yi Kuang, Fei Ma, Fangfang Li, Yingbing Liu, Fan Zhang   +4 more
doaj   +1 more source

Spatial-temporal data-augmentation-based functional brain network analysis for brain disorders identification

Frontiers in Neuroscience, 2023
IntroductionDue to the lack of devices and the difficulty of gathering patients, the small sample size is one of the most challenging problems in functional brain network (FBN) analysis.
Qinghua Liu, Yangyang Zhang, Lingyun Guo, ZhengXia Wang   +3 more
doaj   +1 more source

A GAN-Based Augmentation Scheme for SAR Deceptive Jamming Templates with Shadows

Remote Sensing, 2023
To realize fast and effective synthetic aperture radar (SAR) deception jamming, a high-quality SAR deception jamming template library can be generated by performing sample augmentation on SAR deception jamming templates.
Shinan Lang, Guiqiang Li, Yi Liu, Wei Lu, Qunying Zhang, Kun Chao   +5 more
doaj   +1 more source

Augmenting sampling based controllers with machine learning [PDF]

Proceedings of the ACM SIGGRAPH / Eurographics Symposium on Computer Animation, 2017
Efficient learning of 3D character control still remains an open problem despite of the remarkable recent advances in the field. We propose a new algorithm that combines planning by a sampling-based model-predictive controller and learning from the planned control, which is very noisy.
Hämäläinen, Perttu, Rajamäki, Joose
openaire   +1 more source

Data augmentation for models based on rejection sampling [PDF]

Biometrika, 2016
6 figures.
Rao, Vinayak, Lin, Lizhen, Dunson, David B   +2 more
openaire   +3 more sources

Dynamic Data Augmentation Method for Hyperspectral Image Classification Based on Siamese Structure

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021
At present, deep learning classification researches of hyperspectral usually focus on optimizing the classification model. In essence, most of them did not take special measures for the characteristics of the small sample and imbalanced category ...
Hongmin Gao, Junpeng Zhang, Xueying Cao, Zhonghao Chen, Yiyan Zhang, Chenming Li   +5 more
doaj   +1 more source

Variational Autoencoders for Data Augmentation in Clinical Studies

Applied Sciences, 2023
Sample size estimation is critical in clinical trials. A sample of adequate size can provide insights into a given population, but the collection of substantial amounts of data is costly and time-intensive.
Dimitris Papadopoulos, Vangelis D. Karalis   +1 more
doaj   +1 more source

A Rolling Bearing Fault Diagnosis Based on Conditional Depth Convolution Countermeasure Generation Networks under Small Samples

Sensors, 2022
Aiming at the problems of low fault diagnosis accuracy caused by insufficient samples and unbalanced data sample distribution in bearing fault diagnosis, this paper proposes a fault diagnosis method for rolling bearings referencing conditional deep ...
Cheng Peng, Shuting Zhang, Changyun Li
doaj   +1 more source

Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMC [PDF]

CoRR, 2021
Accepted at AISTATS 2021; added experiments with longer MCMC ...
Jaini, Priyank, Nielsen, Didrik, Welling, Max   +2 more
openaire   +3 more sources

Augmenting source code lines with sample variable values [PDF]

Proceedings of the 26th Conference on Program Comprehension, 2018
Source code is inherently abstract, which makes it difficult to understand. Activities such as debugging can reveal concrete runtime details, including the values of variables. However, they require that a developer explicitly requests these data for a specific execution moment.
Matús Sulír, Jaroslav Porubän
openaire   +2 more sources