Unpaired image translation to mitigate domain shift in liquid argon time projection chamber detector responses

Journal Article · 22 October 2024 · Machine Learning: Science and Technology

DOI: https://doi.org/10.1088/2632-2153/ad849c · OSTI ID:2478421

Huang, Yi  ^[1]; Torbunov, Dmitrii  ^[1]; Viren, Brett ^[1]; Yu, Haiwang  ^[1]; Huang, Jin  ^[1]; Lin, Meifeng  ^[1]; Ren, Yihui  ^[1]

---

1. Brookhaven National Laboratory (BNL), Upton, NY (United States)

Deep learning algorithms often are developed and trained on a training dataset and deployed on test datasets. Any systematic difference between the training and a test dataset may severely degrade the final algorithm performance on the test dataset—what is known as the domain shift problem. This issue is prevalent in many scientific domains where algorithms are trained on simulated data but applied to real-world datasets. Typically, the domain shift problem is solved through various domain adaptation (DA) methods. However, these methods are often tailored for a specific downstream task, such as classification or semantic segmentation, and may not easily generalize to different tasks. This work explores the feasibility of using an alternative way to solve the domain shift problem that is not specific to any downstream algorithm. The proposed approach relies on modern Unpaired Image-to-Image (UI2I) translation techniques, designed to find translations between different image domains in a fully unsupervised fashion. In this study, the approach is applied to a domain shift problem commonly encountered in Liquid Argon Time Projection Chamber (LArTPC) detector research when seeking a way to translate samples between two differently distributed LArTPC detector datasets deterministically. This translation allows for mapping real-world data into the simulated data domain where the downstream algorithms can be run with much less domain-shift-related performance degradation. Conversely, using the translation from the simulated data to a real-world domain can increase the realism of the simulated dataset and reduce the magnitude of any systematic uncertainties. To evaluate the quality of the translations, we use both pixel-wise metrics and a downstream task to measure the effectiveness of UI2I methods for mitigating the domain shift problem. We adapted several popular UI2I translation algorithms to work on scientific data and demonstrated the viability of these techniques for solving the domain shift problem with LArTPC detector data. To facilitate further development of DA techniques for scientific datasets, the ‘Simple Liquid-Argon Track Samples’ dataset used in this study is also published.

• Research Organization: Brookhaven National Laboratory (BNL), Upton, NY (United States)
• Sponsoring Organization: Laboratory-Directed Research and Development (LDRD); USDOE
• Grant/Contract Number: SC0012704
• OSTI ID: 2478421
• Report Number(s): BNL--226339-2024-JAAM
• Journal Information: Machine Learning: Science and Technology, Journal Name: Machine Learning: Science and Technology Journal Issue: 4 Vol. 5; ISSN 2632-2153
• Publisher: IOP PublishingCopyright Statement
• Country of Publication: United States
• Language: English