Related papers: Comparing and improving hybrid deep learning algor…

Deep neural networks have proven increasingly important for automotive scene understanding with new algorithms offering constant improvements of the detection performance. However, there is little emphasis on experiences and needs for…

Particle identification in large high-energy physics experiments typically relies on classifiers obtained by combining many experimental observables. Predicting the probability density function (pdf) of such classifiers in the multivariate…

Real-time data processing is a central aspect of particle physics experiments with high requirements on computing resources. The LHCb experiment must cope with the 30 million proton-proton bunches collision per second rate of the Large…

Deep convolutional neural networks (DCNN for short) are vulnerable to examples with small perturbations. Improving DCNN's robustness is of great significance to the safety-critical applications, such as autonomous driving and industry…

Collider experiments are equipped with trigger systems that rapidly inspect the physics content emerging from collisions to decide whether the resulting products are worth saving for later analysis. One crucial aspect for analyzing the…

Object identification is one of the most fundamental and difficult issues in computer vision. It aims to discover object instances in real pictures from a huge number of established categories. In recent years, deep learning-based object…

For the past year, the HEP.TrkX project has been investigating machine learning solutions to LHC particle track reconstruction problems. A variety of models were studied that drew inspiration from computer vision applications and operated…

We propose a novel strategy for disentangling proton collisions at hadron colliders such as the LHC that considerably improves over the current state of the art. Employing a metric inspired by optimal transport problems as the cost function…

Performance optimization of deep learning models is conducted either manually or through automatic architecture search, or a combination of both. On the other hand, their performance strongly depends on the target hardware and how…

This paper presents a novel method for the reconstruction of interaction vertices in particle collision data. The algorithm is an agglomerative clustering technique designed for high-luminosity environments in current and future…

Hardware accelerations of deep learning systems have been extensively investigated in industry and academia. The aim of this paper is to achieve ultra-high energy efficiency and performance for hardware implementations of deep neural…

The increase in network attacks has necessitated the development of robust and efficient intrusion detection systems (IDS) capable of identifying malicious activities in real-time. In the last five years, deep learning algorithms have…

Predicting human trajectories is a challenging task due to the complexity of pedestrian behavior, which is influenced by external factors such as the scene's topology and interactions with other pedestrians. A special challenge arises from…

Beginning from a basic neural-network architecture, we test the potential benefits offered by a range of advanced techniques for machine learning, in particular deep learning, in the context of a typical classification problem encountered…

In recent years, with the rapid development of computer information technology, the development of artificial intelligence has been accelerating. The traditional geometry recognition technology is relatively backward and the recognition…

Current fine-grained classification approaches often rely on a robust localization of object parts to extract localized feature representations suitable for discrimination. However, part localization is a challenging task due to the large…

Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable…

Deep learning architectures are showing great promise in various computer vision domains including image classification, object detection, event detection and action recognition. In this study, we investigate various aspects of…

High-energy physics experiments rely on reconstruction of the trajectories of particles produced at the interaction point. This is a challenging task, especially in the high track multiplicity environment generated by p-p collisions at the…

Although deep learning has yielded impressive performance for face recognition, many studies have shown that different networks learn different feature maps: while some networks are more receptive to pose and illumination others appear to…