Related papers: Scalable, Proposal-free Instance Segmentation Netw…

We describe the concept and procedure of drifted-charge extraction developed in the MicroBooNE experiment, a single-phase liquid argon time projection chamber (LArTPC). This technique converts the raw digitized TPC waveform to the number of…

The three-dimensional Time-Resolved Lagrangian Particle Tracking (3D TR-LPT) technique has recently advanced flow diagnostics by providing high spatiotemporal resolution measurements under the Lagrangian framework. To fully exploit its…

Single particle imaging (SPI) at X-ray free electron lasers (XFELs) is particularly well suited to determine the 3D structure of particles in their native environment. For a successful reconstruction, diffraction patterns originating from a…

Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform…

Subspace clustering is a powerful unsupervised approach for hyperspectral image (HSI) analysis, but its high computational and memory costs limit scalability. Superpixel segmentation can improve efficiency by reducing the number of data…

While convolutional neural networks have gained impressive success recently in solving structured prediction problems such as semantic segmentation, it remains a challenge to differentiate individual object instances in the scene. Instance…

To avoid the exhaustive search over locations and scales, current state-of-the-art object detection systems usually involve a crucial component generating a batch of candidate object proposals from images. In this paper, we present a simple…

We present the performance of a semantic segmentation network, SparseSSNet, that provides pixel-level classification of MicroBooNE data. The MicroBooNE experiment employs a liquid argon time projection chamber for the study of neutrino…

In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First, we highlight convolution with upsampled filters,…

High-resolution 3D object generation remains a challenging task primarily due to the limited availability of comprehensive annotated training data. Recent advancements have aimed to overcome this constraint by harnessing image generative…

This paper studies the 3D instance segmentation problem, which has a variety of real-world applications such as robotics and augmented reality. Since the surroundings of 3D objects are of high complexity, the separating of different objects…

Particle track reconstruction is the most computationally intensive process in nuclear physics experiments. Traditional algorithms use a combinatorial approach that exhaustively tests track measurements ("hits") to identify those that form…

Computational reconstruction plays a vital role in computer vision and computational photography. Most of the conventional optimization and deep learning techniques explore local information for reconstruction. Recently, nonlocal low-rank…

Clustering high-dimensional datasets is hard because interpoint distances become less informative in high-dimensional spaces. We present a clustering algorithm that performs nonlinear dimensionality reduction and clustering jointly. The…

Knowledge distillation is a form of model compression that allows artificial neural networks of different sizes to learn from one another. Its main application is the compactification of large deep neural networks to free up computational…

As we push the boundaries of performance in various vision tasks, the models grow in size correspondingly. To keep up with this growth, we need very aggressive pruning techniques for efficient inference and deployment on edge devices.…

Models based on Convolutional Neural Networks (CNNs) have been proven very successful for semantic segmentation and object parsing that yield hierarchies of features. Our key insight is to build convolutional networks that take input of…

The goal of salient region detection is to identify the regions of an image that attract the most attention. Many methods have achieved state-of-the-art performance levels on this task. Recently, salient instance segmentation has become an…

Imaging Cherenkov detectors are largely used for particle identification (PID) in nuclear and particle physics experiments, where developing fast reconstruction algorithms is becoming of paramount importance to allow for near real time…

The amount and complexity of data recorded by high energy physics experiments are rapidly growing, and with these grow the difficulties in visualizing such data. To study the physics of neutrinos, a type of elementary particle, scientists…