Related papers: Deep Learning strategies for ProtoDUNE raw data de…

Recent advances in deep learning-based medical image registration have shown that training deep neural networks~(DNNs) does not necessarily require medical images. Previous work showed that DNNs trained on randomly generated images with…

Deep learning has become an increasingly popular and powerful methodology for modern pattern recognition systems. However, many deep neural networks have millions or billions of parameters, making them untenable for real-world applications…

Traditional denoising methods for noise removal have largely relied on handcrafted priors, often perform well in controlled environments but struggle to address the complexity and variability of real noise. In contrast, deep learning-based…

This paper presents a deep learning approach to aid dead-reckoning (DR) navigation using a limited sensor suite. A Recurrent Neural Network (RNN) was developed to predict the relative horizontal velocities of an Autonomous Underwater…

Hyperspectral images (HSIs) are susceptible to various noise factors leading to the loss of information, and the noise restricts the subsequent HSIs object detection and classification tasks. In recent years, learning-based methods have…

We investigate a novel approach for image restoration by reinforcement learning. Unlike existing studies that mostly train a single large network for a specialized task, we prepare a toolbox consisting of small-scale convolutional networks…

Deep convolutional neural networks (CNNs) for image denoising can effectively exploit rich hierarchical features and have achieved great success. However, many deep CNN-based denoising models equally utilize the hierarchical features of…

Deep learning using multi-layer neural networks (NNs) architecture manifests superb power in modern machine learning systems. The trained Deep Neural Networks (DNNs) are typically large. The question we would like to address is whether it…

Cryogenic electron tomography is a technique for imaging biological samples in 3D. A microscope collects a series of 2D projections of the sample, and the goal is to reconstruct the 3D density of the sample called the tomogram.…

Motivated by the advances in 3D sensing technology and the spreading of low-cost robotic platforms, 3D object reconstruction has become a common task in many areas. Nevertheless, the selection of the optimal sensor pose that maximizes the…

Autoencoders are neural network formulations where the input and output of the network are identical and the goal is to identify the hidden representation in the provided datasets. Generally, autoencoders project the data nonlinearly onto a…

In the Coded Aperture Snapshot Spectral Imaging (CASSI) system, deep unfolding networks (DUNs) have demonstrated excellent performance in recovering 3D hyperspectral images (HSIs) from 2D measurements. However, some noticeable gaps exist…

Efficient data selection is essential for improving the training efficiency of deep neural networks and reducing the associated annotation costs. However, traditional methods tend to be computationally expensive, limiting their scalability…

Deep learning, as a highly efficient method for metasurface inverse design, commonly use simulation data to train deep neural networks (DNNs) that can map desired functionalities to proper metasurface designs. However, the assumptions and…

We have developed a convolutional neural network (CNN) that can make a pixel-level prediction of objects in image data recorded by a liquid argon time projection chamber (LArTPC) for the first time. We describe the network design, training…

Image super-resolution and denoising are two important tasks in image processing that can lead to improvement in image quality. Image super-resolution is the task of mapping a low resolution image to a high resolution image whereas…

Object rearranging is one of the most common deformable manipulation tasks, where the robot needs to rearrange a deformable object into a goal configuration. Previous studies focus on designing an expert system for each specific task by…

Deep Neural Networks (DNNs) are ubiquitous in today's computer vision land-scape, despite involving considerable computational costs. The mainstream approaches for runtime acceleration consist in pruning connections (unstructured pruning)…

We develop a novel algorithm for characterizing Deep Sub-Electron Read Noise (DSERN) image sensors. This algorithm is able to simultaneously compute maximum likelihood estimates of quanta exposure, conversion gain, bias, and read noise of…

Deep unfolding networks (DUNs), combining conventional iterative optimization algorithms and deep neural networks into a multi-stage framework, have achieved remarkable accomplishments in Image Restoration (IR), such as spectral imaging…