PanopTag: Simultaneously Tagging All Jets in a Particle Collision Event

TL;DR

PanopTag introduces a novel method for simultaneously tagging all jets in a particle collision event, leveraging event-wide correlations to significantly improve classification performance over traditional independent jet tagging methods.

Contribution

The paper presents PanopTag, a new paradigm that jointly tags all jets in an event using an encoder-decoder architecture, capturing correlations ignored by previous methods.

Findings

Significant performance improvements in heavy-flavor tagging.

Effective exploitation of event-level features and jet correlations.

Outperforms state-of-the-art single-jet tagging baselines.

Abstract

Jet tagging, identifying the origin of jets produced in particle collisions, is a critical classification task in high-energy physics. Despite the revolutionary impact of deep learning on jet tagging over the past decade, the paradigm has remained unchanged. In particular, jets are classified independently, one at a time. This single-jet approach ignores correlations, overlaps, and wider event context between jets. We introduce PanopTag, a new paradigm for jet tagging that departs from traditional single-jet tagging approaches. Rather than classifying jets independently, PanopTag simultaneously tags all jets by employing an encoder-decoder architecture that uses jet kinematics as queries to cross-attend to particle flow object embeddings. We evaluate PanopTag on heavy-flavor $(b/c)$-tagging and demonstrate remarkable performance improvements over state-of-the-art single-jet baselines that are only accessible by exploiting event-level features and correlations between jets.