提出交互场匹配方法，突破静电模型生成局限
Interaction Field Matching: Overcoming Limitations of Electrostatic Models
- 用广义交互场替代传统静电场建模
- 新设计的强相互作用场解决电场建模难题
- 在图像迁移任务中表现优于现有方法
静电场匹配（EFM）是一种基于电容物理原理的新颖数据生成与迁移范式，但其依赖神经网络建模静电场，因需处理电极板外复杂场分布而极具挑战。本文提出交互场匹配（IFM），将EFM推广至更广泛的交互场建模。受夸克与反夸克间强相互作用启发，设计了一种特定交互场实现方式，有效解决了EFM中电场建模的固有问题。我们在一系列玩具数据与图像迁移任务上验证了该方法的有效性。代码已开源：https://github.com/justkolesov/InteractionFieldMatching。
原文摘要 · Abstract (English)
Electrostatic field matching (EFM) has recently appeared as a novel physics-inspired paradigm for data generation and transfer using the idea of an electric capacitor. However, it requires modeling electrostatic fields using neural networks, which is non-trivial because of the necessity to take into account the complex field outside the capacitor plates. In this paper, we propose Interaction Field Matching (IFM), a generalization of EFM which allows using general interaction fields beyond the electrostatic one. Furthermore, inspired by strong interactions between quarks and antiquarks in physics, we design a particular interaction field realization which solves the problems which arise when modeling electrostatic fields in EFM. We show the performance on a series of toy and image data transfer problems. Our code is available at https://github.com/justkolesov/InteractionFieldMatching
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。