ResoSeg: Resonance Tagger using Transformer and Segment Model
Abstract
Deep learning has been widely applied across many areas of experimental high-energy physics, yet existing models address only event-level classification or object tagging and therefore still require reconstruction algorithms tailored to each decay channel. We present the first application of segmentation to resonance tagging at BESIII and introduce ResoSeg, a deep learning model that jointly performs particle-level segmentation and event-level classification, enabling a one-pass analysis of resonance to anything decays while precisely reconstructing the relevant resonance properties. We demonstrate the reconstruction of ηc with e+e-→π+π-hc, hc→γηc, ηc→anything. The model is trained on BESIII-ηc dataset, which is constructed with per-track true labels obtained via a Truth-Matching Algorithm. Experimental results show that the average combined efficiency of ResoSeg is more than double that of the conventional 16-channel approach across energy points from 4.19 to 4.60\,GeV. The model generalizes to unseen energy points, adapts to other ηc production modes through transfer learning, and remains robust against variations in the ηc mass, width, and branching fractions, providing a general, resonance-aware model applicable beyond ηc and BESIII. The source code is available at https://github.com/oashen/ResoSeg.
Related
- A compact, interrogable Tree Tensor Network Jet Tagger on Lund declustering trees
- ceci n'est pas un tagger, can an LLM flavour-tag a jet?
- What the Primary Lund Plane Omits: A Model-Stitching Diagnosis of a Jet-Tagger Representation Gap
- Search for Neutrino-Produced Long-Lived Particles Using the SBND Cosmic Ray Tagger Beam Telescope
- Fast Self-Triggering and Segment-Fitting of Cosmic Muons with a small-Diameter Monitored Drift Tube Detector
BibTeX
@misc{li2026resoseg,
title = {{ResoSeg: Resonance Tagger using Transformer and Segment Model}},
author = {Chunkai Li and Junhao Yin and Ke Li and Jingde Chen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.12610},
eprint = {2609.12610},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.12610},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - ResoSeg: Resonance Tagger using Transformer and Segment Model
AU - Chunkai Li
AU - Junhao Yin
AU - Ke Li
AU - Jingde Chen
PY - 2026
DA - 2026/09/11
PB - arXiv
DO - 10.48550/arxiv.2609.12610
UR - https://arxiv.org/abs/2609.12610
AB - Deep learning has been widely applied across many areas of experimental high-energy physics, yet existing models address only event-level classification or object tagging and therefore still require reconstruction algorithms tailored to each decay channel. We present the first application of segmentation to resonance tagging at BESIII and introduce ResoSeg, a deep learning model that jointly performs particle-level segmentation and event-level classification, enabling a one-pass analysis of resonance to anything decays while precisely reconstructing the relevant resonance properties. We demonstrate the reconstruction of η_c with e^+e^-→π^+π^-h_c, h_c→γη_c, η_c→anything. The model is trained on BESIII-η_c dataset, which is constructed with per-track true labels obtained via a Truth-Matching Algorithm. Experimental results show that the average combined efficiency of ResoSeg is more than double that of the conventional 16-channel approach across energy points from 4.19 to 4.60\,GeV. The model generalizes to unseen energy points, adapts to other η_c production modes through transfer learning, and remains robust against variations in the η_c mass, width, and branching fractions, providing a general, resonance-aware model applicable beyond η_c and BESIII. The source code is available at https://github.com/oashen/ResoSeg.
ER -