English

Mode-locking Theory for Long-Range Interaction in Artificial Neural Networks

Computer Vision and Pattern Recognition 2023-03-13 v1

Abstract

Visual long-range interaction refers to modeling dependencies between distant feature points or blocks within an image, which can significantly enhance the model's robustness. Both CNN and Transformer can establish long-range interactions through layering and patch calculations. However, the underlying mechanism of long-range interaction in visual space remains unclear. We propose the mode-locking theory as the underlying mechanism, which constrains the phase and wavelength relationship between waves to achieve mode-locked interference waveform. We verify this theory through simulation experiments and demonstrate the mode-locking pattern in real-world scene models. Our proposed theory of long-range interaction provides a comprehensive understanding of the mechanism behind this phenomenon in artificial neural networks. This theory can inspire the integration of the mode-locking pattern into models to enhance their robustness.

Keywords

Cite

@article{arxiv.2303.05695,
  title  = {Mode-locking Theory for Long-Range Interaction in Artificial Neural Networks},
  author = {Xiuxiu Bai and Shuaishuai Zhao and Yao Gao and Zhe Liu},
  journal= {arXiv preprint arXiv:2303.05695},
  year   = {2023}
}

Comments

10 pages, 6 figures

R2 v1 2026-06-28T09:10:28.632Z