CNN on `Top': In Search of Scalable & Lightweight Image-based Jet Taggers
High Energy Physics - Phenomenology
2026-02-23 v2 Computational Physics
Data Analysis, Statistics and Probability
Abstract
While Transformer-based and standard Graph Neural Networks (GNNs) have proven to be the best performers in classifying different types of jets, they require substantial computational power. We explore the scope of using a lightweight and scalable version of EfficientNet architecture, along with global features of the jet. The end product is computationally inexpensive but is capable of competitive performance. We showcase the efficacy of our network in tagging top-quark jets in a sea of other light quark and gluon jets. The work also sheds light on the importance of global features for both the accuracy and the apparent redundancy of the network's complexity.
Cite
@article{arxiv.2512.05031,
title = {CNN on `Top': In Search of Scalable & Lightweight Image-based Jet Taggers},
author = {Rajneil Baruah and Subhadeep Mondal and Sunando Kumar Patra and Satyajit Roy},
journal= {arXiv preprint arXiv:2512.05031},
year = {2026}
}
Comments
14 pages, 4 figures, 2 tables, version sent to EPJC