Jet-images: computer vision inspired techniques for jet tagging

By J. Cogan, Michael Kagan, E. Strauss, Ariel Schwarztman. 2014

221 citations recorded by the source corpus.

We introduce a novel approach to jet tagging and classification through the use of techniques inspired by computer vision. Drawing parallels to the problem of facial recognition in images, we define a jet-image using calorimeter towers as the elements of the image and establish jet-image preprocessing methods. For the jet-image processing step, we develop a discriminant for classifying the jet-images derived using Fisher discriminant analysis. The effectiveness of the technique is shown within the context of identifying boosted hadronic W boson decays with respect to a background of quark- and gluoninitiated jets. Using Monte Carlo simulation, we demonstrate that the performance of this technique introduces additional discriminating power over other substructure approaches, and gives significant insight into the internal structure of jets.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Nuclear and High Energy Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Nuclear and High Energy Physics

Citations in the corpus

Learning Particle Physics by Example: Location-Aware Generative Adversarial Networks for Physics Synthesis (2017, methodology): “We start by tackling a constrained version of the larger problem, where we use the concept of a jet image [19] to show that the idealized 2D radiation pattern from high energy quarks and gluons can be eﬃciently and eﬀectively reproduced by a GAN.”
Jet substructure at the Large Hadron Collider: A review of recent advances in theory and machine learning (2017, unknown): “The first applications of DNNs using all of the available information [533, 534, 535] represented jets as images(3) [537].”
Deep learning in color: towards automated quark/gluon jet discrimination (2016, methodology): “For each jet in a given pT range, we constructed a jet image, following [10, 12].”
QCD-aware recursive neural networks for jet physics (2017, methodology): “More recently, the success of deep convolutional networks has triggered a new body of work in jet physics, shifting the paradigm from engineering input features to learning them automatically from raw data, e.g., as in these works treating jets as images [1{7].”
Scientific discovery in the age of artificial intelligence (2023, background): “Examples of AI applications in scientific experiments include visualization regions of spacetime such as black holes 5 , capturing a physics particle collision 51 , improving the resolution of live-cell images 52 and better detection of cell types across biological contexts 53 .”
Jet Substructure Classification in High-Energy Physics with Deep Neural Networks (2016, background): “[25] Josh Cogan, Michael Kagan, Emanuel Strauss, and Ariel Schwarztman.”
Energy flow networks: deep sets for particle jets (2018, methodology): “parable classication performance with similar information. The other machine learning architectures we compare to are a DNN trained on the Nsubjettiness basis [23,67,68], a CNN trained on jet images [4,5,8], and a linear classier trained on the energy ow basis [28]. Their performance, as given by th”
Jet-images — deep learning edition (2015, background): “[1] • Treat the detector as a camera — calorimeter towers as pixels, and depositions as intensity 3 - Generic overview slide”
Parton Shower Uncertainties in Jet Substructure Analyses with Deep Neural Networks (2016, background): “Signals produced by the LHC detectors may be processed into pixelated jet images [20], and machine learning algorithms can be adapted to discriminate between a signal (such as h → b ¯ b decays or boosted hadronic top decays [21]) and background.”
Playing tag with ANN: boosted top identification with pattern recognition (2015, background): “[39] studied jet substructure as an image recognition problem in the context of boosted W tagging as well gluon/quark discrimination.”
JUNIPR: a framework for unsupervised machine learning in particle physics (2018, methodology): “over. One way of preprocessing the raw data in a fairly unbiased way is through the use of jet images, which contain as pixel intensities the energy deposited by jet constituents in calorimeter cells [19]. Jet images invite the use of techniques from image recognition to discriminate jets of dierent”
Energy flow polynomials: a complete linear basis for jet substructure (2017, background): “• The jet images approach [50] treats calorimeter deposits as pixels and the jet as an image, often using convolutional neural networks to determine a classifier.”