Related papers: Attention-Based Generative Neural Image Compressio…
Visual navigation has received significant attention recently. Most of the prior works focus on predicting navigation actions based on semantic features extracted from visual encoders. However, these approaches often rely on large datasets…
It is very difficult to find archival images of solar system objects. While regular archive searches can find images at a fixed location, they cannot find images of moving targets. Archival images have become increasingly useful to galactic…
Saturation affects a significant rate of images recorded by the Atmospheric Imaging Assembly on the Solar Dynamics Observatory. This paper describes a computational method and a technological pipeline for the de-saturation of such images,…
Convolutional layers are an integral part of many deep neural network solutions in computer vision. Recent work shows that replacing the standard convolution operation with mechanisms based on self-attention leads to improved performance on…
Land-use monitoring is fundamental for spatial planning, particularly in view of compound impacts of growing global populations and climate change. Despite existing applications of deep learning in land use monitoring, standard…
We describe an Artificial Neural Network (ANN) approach to classification of galaxy images and spectra. ANNs can replicate the classification of galaxy images by a human expert to the same degree of agreement as that between two human…
We present a Python tool to generate a standard dataset from solar images that allows for user-defined selection criteria and a range of pre-processing steps. Our Python tool works with all image products from both the Solar and…
The Deep Space Network (DSN) is NASA's largest network of antenna facilities that generate a large volume of multivariate time-series data. These facilities contain DSN antennas and transmitters that undergo degradation over long periods of…
In the field of robotics, event-based cameras are emerging as a promising low-power alternative to traditional frame-based cameras for capturing high-speed motion and high dynamic range scenes. This is due to their sparse and asynchronous…
Attention mechanism has been regarded as an advanced technique to capture long-range feature interactions and to boost the representation capability for convolutional neural networks. However, we found two ignored problems in current…
In state-of-the-art deep neural networks, both feature normalization and feature attention have become ubiquitous. % with significant performance improvement shown in a vast amount of tasks. They are usually studied as separate modules,…
Lossless image compression is an essential research field in image compression. Recently, learning-based image compression methods achieved impressive performance compared with traditional lossless methods, such as WebP, JPEG2000, and FLIF.…
Transformers have become the de facto standard for a wide range of tasks, from image classification to physics simulations. Despite their impressive performance, the quadratic complexity of standard Transformers in both memory and time with…
Accelerated MRI involves collecting partial $k$-space measurements to reduce acquisition time, patient discomfort, and motion artifacts, and typically uses regular undersampling patterns or human-designed schemes. Recent works have studied…
Optical neural networks (ONNs) perform extensive computations using photons instead of electrons, resulting in passively energy-efficient and low-latency computing. Among various ONNs, the diffractive optical neural networks (DONNs)…
Semantic segmentation models based on convolutional neural networks (CNNs) have gained much attention in relation to remote sensing and have achieved remarkable performance for the extraction of buildings from high-resolution aerial images.…
We describe a novel scheme for analyzing particle detector measurements when a well-calibrated, similarly instrumented spacecraft is present in a similar orbit. To prepare ground truth from measurements provided by a reference spacecraft,…
Task-agnostic prompt compression leverages the redundancy in natural language to reduce computational overhead and enhance information density within prompts, especially in long-context scenarios. Existing methods predominantly rely on…
Radiation exposure in positron emission tomography (PET) imaging limits its usage in the studies of radiation-sensitive populations, e.g., pregnant women, children, and adults that require longitudinal imaging. Reducing the PET radiotracer…
Recently, a homogenization procedure has been proposed, based on the tight lower bounds of the Bergman-Milton formulation, and successfully applied to dilute ternary nanocomposites to predict optical data without using any fitting…