Related papers: The ONSEN Data Reduction System for the Belle II P…

As DenseNet conserves intermediate features with diverse receptive fields by aggregating them with dense connection, it shows good performance on the object detection task. Although feature reuse enables DenseNet to produce strong features…

We describe the principles and performance of the first-level ("L1") hardware track trigger of Belle II, based on neural networks. The networks use as input the results from the standard Belle II trigger, which provides "2D" track…

The Belle II experiment at the SuperKEKB collider in Japan is designed to indirectly probe new physics using approximately 50 times the data recorded by its predecessor. An accurate determination of the decay-point position of subatomic…

The Belle II experiment at the SuperKEKB collider at KEK, Tsukuba, Japan has successfully started taking data with the full detector in March 2019. Belle II is a luminosity frontier experiment of the new generation to search for physics…

It is well known that attention mechanisms can effectively improve the performance of many CNNs including object detectors. Instead of refining feature maps prevalently, we reduce the prohibitive computational complexity by a novel attempt…

Current perception models in autonomous driving have become notorious for greatly relying on a mass of annotated data to cover unseen cases and address the long-tail problem. On the other hand, learning from unlabeled large-scale collected…

Incremental anomaly detection aims to sequentially identify defects in industrial product lines but suffers from catastrophic forgetting, primarily due to knowledge overwriting during parameter updates and feature conflicts between tasks.…

During the past decade, implementing reconstruction algorithms on hardware has been at the center of much attention in the field of real-time reconstruction in Compressed Sensing (CS). Orthogonal Matching Pursuit (OMP) is the most widely…

The experiments at LHC are implementing novel and challenging detector upgrades for the High Luminosity LHC, among which the tracking systems. This paper reports on performance studies, illustrated by an electron trigger, using a simplified…

This paper reports on the development of a resource-efficient FPGA-based neural network regression model for potential applications in the future hardware muon trigger system of the ATLAS experiment at the Large Hadron Collider (LHC).…

An increasing need of running Convolutional Neural Network (CNN) models on mobile devices with limited computing power and memory resource encourages studies on efficient model design. A number of efficient architectures have been proposed…

Urban informatics explore data science methods to address different urban issues intensively based on data. The large variety and quantity of data available should be explored but this brings important challenges. For instance, although…

DEPFET pixel detectors are unique devices in terms of energy and spatial resolution because very low noise (ENC = 2.2e at room temperature) operation can be obtained by implementing the amplifying transistor in the pixel cell itself. Full…

The complexity of event-based object detection (OD) poses considerable challenges. Spiking Neural Networks (SNNs) show promising results and pave the way for efficient event-based OD. Despite this success, the path to efficient SNNs on…

Convolutional neural network (CNN) accelerators are being widely used for their efficiency, but they require a large amount of memory, leading to the use of a slow and power consuming external memory. This paper exploits two schemes to…

The Belle II experiment is a high-energy physics experiment at the SuperKEKB electron-positron collider. Using Belle II data, high precision measurement of rare decays and CP-violation in heavy quarks and leptons can be performed to probe…

Stencil computation is an extensively-utilized class of scientific-computing applications that can be efficiently accelerated by graphics processing units (GPUs). Out-of-core approaches enable a GPU to handle large stencil codes whose data…

Convolutional Neural Networks (CNNs) have proven to be extremely accurate for image recognition, even outperforming human recognition capability. When deployed on battery-powered mobile devices, efficient computer architectures are required…

Computational complexity and storage requirements are crucial factors influencing the performance and efficiency of convolutional neural networks (CNNs) in resource-constrained environments. This paper presents a high-performance embedded…

Object detection problem solving has developed greatly within the past few years. There is a need for lighter models in instances where hardware limitations exist, as well as a demand for models to be tailored to mobile devices. In this…