Nonlocal Neural Networks, Nonlocal Diffusion and Nonlocal Modeling
This work addresses the need for more stable and deeper nonlocal networks in computer vision, representing an incremental improvement over existing methods.
The paper tackled the problem of understanding and improving nonlocal neural networks by analyzing their diffusion and damping effects, resulting in a new nonlocal block formulation that enables deeper structures with stable dynamics.
Nonlocal neural networks have been proposed and shown to be effective in several computer vision tasks, where the nonlocal operations can directly capture long-range dependencies in the feature space. In this paper, we study the nature of diffusion and damping effect of nonlocal networks by doing spectrum analysis on the weight matrices of the well-trained networks, and then propose a new formulation of the nonlocal block. The new block not only learns the nonlocal interactions but also has stable dynamics, thus allowing deeper nonlocal structures. Moreover, we interpret our formulation from the general nonlocal modeling perspective, where we make connections between the proposed nonlocal network and other nonlocal models, such as nonlocal diffusion process and Markov jump process.