Large and diverse data is crucial to train object detection systems properly and achieve satisfactory prediction performance. However, in some areas, such as ma rine science, gathering sufficient data is challenging and ...

Deep neural networks consume an excessive amount of hardware resources, making them difficult to deploy to real-time systems. Previous work in the field of network compression lack the explicit hardware feedback necessary ...

This work examines the applicability of the deep learning models to pattern recognition in acoustic ocean data. The features of the dataset include noise, data scarcity and the lack of labeled samples. A deep learning ...

This thesis tries to find a methodology that create a working pipeline for building facade parsing, which allows to access large scale panorama imagery from Google Street View (GSV) and implement on deep learning models. ...

Previous research had shown that generative adversarial networks (GANs) are capable of despeckling echocardiograms (echos) through image-to-image translation in real-time once trained. However, only limited information ...

Micro/Nano-electro-mechanical-systems (MEMS/NEMS) are often hailed as disruptive technologies, enabling highly precise measurements across a wide range of applications. In this project we focus on resonator-type MEMS, ...

The need for extensive manual labor in annotating video datasets causes a scarcity of them. Without video datasets of good quality and sufficient diversity, the research and development of machine learning algorithms in ...