Related papers: Shallow Transits -- Deep Learning II: Identify Ind…

The detection of gravitational waves is considered to be one of the most magnificent discoveries of the century. Due to the high computational cost of matched filtering pipeline, there is a hunt for an alternative powerful system. I…

Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards. Here, we address three of its most prominent hurdles, namely, i) the adaptation of a single…

Among the group of extrasolar planets, transiting planets provide a great opportunity to obtain direct measurements for the basic physical properties, such as mass and radius of these objects. These planets are therefore highly important in…

Identifying the positions of granular particles from experimental images is often complicated by their partial overlap in two dimensional projections. Uneven backgrounds and inhomogeneous illuminations can add to the challenge. Conventional…

Semantic segmentation is the pixel-wise labelling of an image. Since the problem is defined at the pixel level, determining image class labels only is not acceptable, but localising them at the original image pixel resolution is necessary.…

We propose a novel weakly-supervised semantic segmentation algorithm based on Deep Convolutional Neural Network (DCNN). Contrary to existing weakly-supervised approaches, our algorithm exploits auxiliary segmentation annotations available…

Accurate measuring the location and orientation of individual particles in a beam monitoring system is of particular interest to researchers in multiple disciplines. Among feasible methods, gaseous drift chambers with hybrid pixel sensors…

We present a technique for verifying or refuting exoplanet candidates from the Transiting Exoplanet Survey Satellite (TESS) mission by searching for nearby eclipsing binary stars using higher-resolution archival images from ground-based…

Convolutional neural networks are the most widely used deep learning algorithms for traffic signal classification till date but they fail to capture pose, view, orientation of the images because of the intrinsic inability of max pooling…

We propose to take a novel approach to robot system design where each building block of a larger system is represented as a differentiable program, i.e. a deep neural network. This representation allows for integrating algorithmic planning…

This paper addresses the task of set prediction using deep learning. This is important because the output of many computer vision tasks, including image tagging and object detection, are naturally expressed as sets of entities rather than…

Despite significant advancements, segmentation based on deep neural networks in medical and surgical imaging faces several challenges, two of which we aim to address in this work. First, acquiring complete pixel-level segmentation labels…

Graph Nerual Networks (GNNs) are effective models in graph embedding. It extracts shallow features and neighborhood information by aggregating neighbor information to learn the embedding representation of different nodes. However, the local…

In the near-future, dedicated telescopes observe Earth-like exoplanets in reflected light, allowing their characterization. Because of the huge distances, every exoplanet will be a single pixel, but temporal variations in its spectral flux…

In this paper we present a two-step neural network model to separate detections of solar system objects from optical and electronic artifacts in data obtained with the "Asteroid Terrestrial-impact Last Alert System" (ATLAS), a near-Earth…

Semantic segmentation is a crucial component for perception in automated driving. Deep neural networks (DNNs) are commonly used for this task and they are usually trained on a closed set of object classes appearing in a closed operational…

Although deep neural networks have achieved remarkable results for the task of semantic segmentation, they usually fail to generalize towards new domains, especially when performing synthetic-to-real adaptation. Such domain shift is…

Targeted observations of possible exomoon host systems will remain difficult to obtain and time-consuming to analyze in the foreseeable future. As such, time-domain surveys such as Kepler, K2 and TESS will continue to play a critical role…

We present a novel method for extracting moving objects from TESS data using machine learning. Our approach uses two stacked 3D U-Nets with skip connections, which we call a W-Net, to filter background and identify pixels containing moving…

Deep learning has made significant progress in computer vision, specifically in image classification, object detection, and semantic segmentation. The skip connection has played an essential role in the architecture of deep neural…