A Non-Local Block With Adaptive Regularization Strategy

Zhonggui Sun, Huichao Sun, Mingzhu Zhang,Jie Li,Xinbo Gao

IEEE SIGNAL PROCESSING LETTERS(2024)

引用 0|浏览9
暂无评分
摘要
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.
更多
查看译文
关键词
Adaptive regularization,deep convolutional neural network,non-local block,receptive field,theoretical interpretation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要