Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
Datasets
State of the Art

Support

Contact
Pricing
Terms of Service
Privacy Policy
About

point-cloud-classification-1

Jet Tagging

3260 papers • 126 benchmarks • 313 datasets

Jet tagging is the process of identifying the type of elementary particle that initiates a "jet", i.e., a collimated spray of outgoing particles. It is essentially a classification task that aims to distinguish jets arising from particles of interest, such as the Higgs boson or the top quark, from other less interesting types of jets.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in point-cloud-classification-1

Trend

Dataset

Best Model

Actions

JetClass

Libraries

Use these libraries to find point-cloud-classification-1 models and implementations

jet-universe/particle_transformer

2 papers 73

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

ParticleNet: Jet Tagging via Particle Clouds

H. Qu, L. Gouskos•Thu Feb 21 2019

This work proposes ParticleNet, a customized neural network architecture using Dynamic Graph Convolutional Neural Network for jet tagging problems that achieves state-of-the-art performance on two representative jet tagging benchmarks and is improved significantly over existing methods.

285

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Variational autoencoders for anomalous jet tagging

T. Golling, Taoli Cheng, J. Arguin, Julien Leissner-Martin, Jacinthe Pilette•Thu Jul 02 2020

OE, in the context of jet tagging, is employed to facilitate two goals: increasing sensitivity of outlier detection and decorrelating jet mass, and is observed to facilitate excellent results from both aspects.

84 0

Paper Graph

Jet tagging in the Lund plane with graph networks

H. Qu, F. Dreyer•Mon Dec 14 2020

This article introduces LundNet, a novel jet tagging method which relies on graph neural networks and an efficient description of the radiation patterns within a jet to optimally disentangle signatures of boosted objects from background events, showing significantly improved performance for top tagging compared to existing state-of-the-art algorithms.

84 0

Paper Graph

Point cloud transformers applied to collider physics

F. Canelli, V. Mikuni•Mon Feb 08 2021

A modified transformer network called point cloud transformer is applied as a method to incorporate the advantages of the transformer architecture to an unordered set of particles resulting from collision events to compare the performance with other strategies.

68 0

Paper Graph

Particle Transformer for Jet Tagging

H. Qu, Congqiao Li, Sitian Qian•Mon Feb 07 2022

A new Transformer-based architecture for jet tagging, called Particle Transformer (ParT), which achieves higher tagging performance than a plain Transformer and surpasses the previous state-of-the-art, ParticleNet, by a large margin.

164 0

Paper Graph

Improving Robustness of Jet Tagging Algorithms with Adversarial Training

Annika Stein, X. Coubez, S. Mondal, A. Novák, A. Schmidt•Thu Mar 24 2022

This work investigates the classifier response to input data with injected mismodelings and probes the vulnerability of flavor tagging algorithms via application of adversarial attacks and presents an adversarial training strategy that mitigates the impact of such simulated attacks and improves the classifiers robustness.

9 0

Paper Graph

Do graph neural networks learn traditional jet substructure?

Javier Mauricio Duarte, Raghav Kansal, Farouk Mokhtar•Wed Nov 16 2022

The decision-making process for one such state-of-the-art network, ParticleNet, is explored by looking for relevant edge connections identified using the layerwise-relevance propagation technique.

12 0

Paper Graph

Boost invariant polynomials for efficient jet tagging

José M. Muñoz, Ilyes Batatia, C. Ortner•Sat Jul 16 2022

It is shown that, for both supervised and unsupervised tasks, integrating BIPs with conventional classification techniques leads to models achieving high accuracy on jet tagging benchmarks while being orders of magnitudes faster to train and evaluate than contemporary deep learning systems.

17 0

Paper Graph

Adding a benchmark result helps the community track progress.

Jet Tagging | State-of-the-Art