A Non-Local Block
with Adaptive
Regularization Strategy
Zhonggui Sun1,2,
Huichao Sun1, Mingzhu Zhang1, Jie Li2, Xinbo Gao3
1. School of Mathematical Sciences, Liaocheng University, Liaocheng,252000, China
2. School of Electronic Engineering, Xidian University, Xi’an, 710071, China
3. Chongqing Key Laboratory of Image Cognition,
Chongqing University of Posts and Telecommunications, Chongqing 400065,
China
Abstract
Non-local block (NLB) is a breakthrough
technology in computer vision. It greatly boosts the capability of deep
convolutional neural networks (CNNs) to capture long-range dependencies. As the
critical component of NLB, non-local operation can be considered a network-based
implementation of the well-known non-local means filter (NLM). Drawing on the
solid theoretical foundation of NLM, we provide an innovative interpretation of
the non-local
operation.
Specifically, it is formulated as an optimization problem regularized by Shannon
entropy with a fixed parameter. Building on this insight, we further introduce
an adaptive regularization strategy to enhance NLB and get a novel non-local
block named ARNLB. Preliminary experiments on semantic segmentation demonstrate
its effectiveness. The code of ARNLB is accessible at
http://www.diplab.net/lunwen/arnlb.htm.
Paper
Z. Sun, H. Sun, M. Zhang, J. Li, X. Gao. A Non-Local Block with Adaptive Regularization Strategy. IEEE Signal Processing Letters (IEEE-SPL)，vol. 31, pp. 331-335, 2024. code
Visualization Results
Theories
---------------------------------------------------------------------------------------------------
---------------------------------------------------------------------------------------------------
-----------------------------------------------------------------------------------------------------