Abstract
Abstract
We use Fréchet Inception Distance (FID) measured in the
latent spaces of pre-trained, fine-tuned and custom-made inception
networks to evaluate Generative Adversarial Networks (GANs)
developed by the COherent Muon to Electron Transition (COMET)
collaboration to generate sequences of background hits in a
Cylindrical Drift Chamber (CDC). We validate the convergence of the
GANs' training and show that the use of self-attention layers
reduces FID. Our method enables the use of FID as an evaluation
metric even when an application-specific inception network is not
readily available, making it transferable to other GAN applications
in High Energy Physics.
Subject
Mathematical Physics,Instrumentation
Reference15 articles.
1. COMET Phase-I Technical Design Report;Abramishvili;PTEP,2020
2. COMET Muon Conversion Experiment in J-PARC;Lee,2018
3. SINDRUM II;van der Schaaf;SciPost Phys. Proc.,2021
4. Generative Adversarial Networks;Goodfellow,2014