[论文解读] NASNet: A Neuron Attention Stage-by-Stage Net for Single Image Deraining

Qin Xu, Zhilin Wang|arXiv (Cornell University)|Dec 6, 2019

Image Enhancement Techniques参考文献 27被引用 36

一句话总结

NASNet 引入一种轻量级的神经元注意力机制和逐阶段网络，以解决单图像去雨中的多种降雨模型问题，达到强泛化和领先的性能。

ABSTRACT

Images captured under complicated rain conditions often suffer from noticeable degradation of visibility. The rain models generally introduce diversity visibility degradation, which includes rain streak, rain drop as well as rain mist. Numerous existing single image deraining methods focus on the only one type rain model, which does not have strong generalization ability. In this paper, we propose a novel end-to-end Neuron Attention Stage-by-Stage Net (NASNet), which can solve all types of rain model tasks efficiently. For one thing, we pay more attention on the Neuron relationship and propose a lightweight Neuron Attention (NA) architectural mechanism. It can adaptively recalibrate neuron-wise feature responses by modelling interdependencies and mutual influence between neurons. Our NA architecture consists of Depthwise Conv and Pointwise Conv, which has slight computation cost and higher performance than SE block by our contrasted experiments. For another, we propose a stage-by-stage unified pattern network architecture, the stage-by-stage strategy guides the later stage by incorporating the useful information in previous stage. We concatenate and fuse stage-level information dynamically by NA module. Extensive experiments demonstrate that our proposed NASNet significantly outperforms the state-of-theart methods by a large margin in terms of both quantitative and qualitative measures on all six public large-scale datasets for three rain model tasks.

研究动机与目标

• 解决在单一降雨模型上训练的去雨方法泛化能力差的问题
• 开发一种轻量级的逐神经元注意力机制以重新校准特征响应
• 设计一个逐阶段的统一架构，在各阶段传播有用信息
• 使用神经元注意力模块动态融合阶段级信息
• 在六个公开数据集和三个降雨模型任务上展示出色的性能

提出的方法

• 提出使用 Depthwise Conv 和 Pointwise Conv 的 Neuron Attention (NA) 机制来重新校准逐神经元特征
• 引入一个逐阶段的统一模式网络，其中后续阶段由前期阶段引导
• 通过 NA 模块动态连接和融合阶段级信息
• 针对多种降雨模型的端到端去雨训练框架
• 在六个公开数据集的三个降雨模型任务上评估 NASNet

实验结果

研究问题

• RQ1 一个以神经元为焦点的注意力机制是否能在多样化的降雨模型中提高去雨性能？
• RQ2 一个逐阶段结构在阶段间传播信息是否能改善泛化和性能？
• RQ3 NA 模块在性能和计算方面相比现有的注意力模块（如 SE）表现如何？
• RQ4 NASNet 是否在多种降雨模型任务和数据集上有效，而不专门针对单一模型？

主要发现

• NASNet 在所有六个公开的大规模数据集的三个降雨模型任务上显著超越了最先进的方法
• 实验中，Neuron Attention 机制在 Depthwise 与 Pointwise 卷积下的性能优于 SE 块
• 逐阶段设计使得前期阶段对后期阶段具有信息性引导
• 通过 NA 的阶段级信息的动态拼接与融合提升去雨结果
• 大量实验证明在定量和定性方面均优于竞争方法