Related papers: An autoencoder for compressing angle-resolved phot…
The volume of remote sensing data is experiencing rapid growth, primarily due to the plethora of space and air platforms equipped with an array of sensors. Due to limited hardware and battery constraints the data is transmitted back to…
A learning-based adaptive loop filter is developed for the Geometry-based Point Cloud Compression (G-PCC) standard to reduce attribute compression artifacts. The proposed method first generates multiple Most-Probable Sample Offsets (MPSOs)…
Quantitative ultrasound, e.g., speed-of-sound (SoS) in tissues, provides information about tissue properties that have diagnostic value. Recent studies showed the possibility of extracting SoS information from pulse-echo ultrasound raw data…
Autoencoders are composed of coding and decoding units, hence they hold the inherent potential of high-performance data compression and signal compressed sensing. The main disadvantages of current autoencoders comprise the following several…
The process of recording Electroencephalography (EEG) signals is onerous and requires massive storage to store signals at an applicable frequency rate. In this work, we propose the EventRelated Potential Encoder Network (ERPENet); a…
Compressing convolutional neural networks (CNNs) has received ever-increasing research focus. However, most existing CNN compression methods do not interpret their inherent structures to distinguish the implicit redundancy. In this paper,…
Optical and hybrid convolutional neural networks (CNNs) recently have become of increasing interest to achieve low-latency, low-power image classification and computer vision tasks. However, implementing optical nonlinearity is challenging,…
Angle-resolved photoemission spectroscopy (ARPES) is used to study the mass renormalization of the charge carriers in the high-T_c superconductor (Pb,Bi)_2Sr_2CaCu_2O_8 in the vicinity of the (pi,0) point in the superconducting and the…
Significant efforts are being invested to bring state-of-the-art classification and recognition to edge devices with extreme resource constraints (memory, speed, and lack of GPU support). Here, we demonstrate the first deep network for…
We propose a computationally efficient wrapper feature selection method - called Autoencoder and Model Based Elimination of features using Relevance and Redundancy scores (AMBER) - that uses a single ranker model along with autoencoders to…
Accurately modeling and forecasting complex systems governed by partial differential equations (PDEs) is crucial in various scientific and engineering domains. However, traditional numerical methods struggle in real-world scenarios due to…
After an extended introduction, the thesis considers the electronic properties of BSCCO and the recent progress in understanding the electronic structure of this material. The main result of this part of the work is a model of the Green's…
Compressive sensing (CS) is an effective approach for fast Magnetic Resonance Imaging (MRI). It aims at reconstructing MR images from a small number of under-sampled data in k-space, and accelerating the data acquisition in MRI. To improve…
Nowadays U-net-like FCNs predominate various biomedical image segmentation applications and attain promising performance, largely due to their elegant architectures, e.g., symmetric contracting and expansive paths as well as lateral…
Research in the past years introduced Steered Mixture-of-Experts (SMoE) as a framework to form sparse, edge-aware models for 2D- and higher dimensional pixel data, applicable to compression, denoising, and beyond, and capable to compete…
Angle-resolved photoemission spectroscopy is the leading tool for studying the symmetry and structure of the order parameter in superconductors. The recent improvement of the technique made it possible to detect the superconducting energy…
Multisensor fusion is essential for autonomous vehicles to accurately perceive, analyze, and plan their trajectories within complex environments. This typically involves the integration of data from LiDAR sensors and cameras, which…
Image-based anomaly detection systems are of vital importance in various manufacturing applications. The resolution and acquisition rate of such systems is increasing significantly in recent years under the fast development of image sensing…
Autoencoders learn data representations (codes) in such a way that the input is reproduced at the output of the network. However, it is not always clear what kind of properties of the input data need to be captured by the codes. Kernel…
Self-supervised learning has become a central strategy for representation learning, but the majority of architectures used for encoding data have only been validated on regularly-sampled inputs such as images, audios. and videos. In many…