NASNet: A Neuron Attention Stage-by-Stage Net for Single Image Deraining

TL;DR

This paper introduces NASNet, an end-to-end neural network with a novel neuron attention mechanism and stage-by-stage architecture, achieving superior performance in single image deraining across diverse rain models.

Contribution

The paper presents a lightweight neuron attention module and a stage-by-stage network design that generalizes well to multiple rain types, outperforming existing methods.

Findings

Significantly outperforms state-of-the-art methods on six datasets.

Effective modeling of neuron relationships improves deraining performance.

Stage-by-stage strategy enhances information fusion and generalization.

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.