A De-raining semantic segmentation network for real-time foreground segmentation

TL;DR

This paper introduces DRSNet, a lightweight real-time semantic segmentation network tailored for rainy environments, utilizing multi-scale dilated convolutions and asymmetric skip connections to enhance accuracy while maintaining efficiency.

Contribution

The paper proposes a novel lightweight network with MultiScaleSE Block and Asymmetric Skip for improved rainy environment segmentation, achieving state-of-the-art results with low computational cost.

Findings

Achieves state-of-the-art accuracy on UAS-add-rain and BPS-add-rain benchmarks.

Operates in real-time with only 0.54M parameters and 0.20 GFLOPs.

Outperforms similar networks in speed and accuracy at under 1 GFLOPs.

Abstract

Few researches have been proposed specifically for real-time semantic segmentation in rainy environments. However, the demand in this area is huge and it is challenging for lightweight networks. Therefore, this paper proposes a lightweight network which is specially designed for the foreground segmentation in rainy environments, named De-raining Semantic Segmentation Network (DRSNet). By analyzing the characteristics of raindrops, the MultiScaleSE Block is targetedly designed to encode the input image, it uses multi-scale dilated convolutions to increase the receptive field, and SE attention mechanism to learn the weights of each channels. In order to combine semantic information between different encoder and decoder layers, it is proposed to use Asymmetric Skip, that is, the higher semantic layer of encoder employs bilinear interpolation and the output passes through pointwise convolution, then added element-wise to the lower semantic layer of decoder. According to the control experiments, the performances of MultiScaleSE Block and Asymmetric Skip compared with SEResNet18 and Symmetric Skip respectively are improved to a certain degree on the Foreground Accuracy index. The parameters and the floating point of operations (FLOPs) of DRSNet is only 0.54M and 0.20GFLOPs separately. The state-of-the-art results and real-time performances are achieved on both the UESTC all-day Scenery add rain (UAS-add-rain) and the Baidu People Segmentation add rain (BPS-add-rain) benchmarks with the input sizes of 192*128, 384*256 and 768*512. The speed of DRSNet exceeds all the networks within 1GFLOPs, and Foreground Accuracy index is also the best among the similar magnitude networks on both benchmarks.