Faster SCDNet: Real-Time Semantic Segmentation Network with Split Connection and Flexible Dilated Convolution

Abstract

Recently, semantic segmentation has been widely applied in various realistic scenarios. Many semantic segmentation backbone networks use various forms of dense connection to improve the efficiency of gradient propagation in the network. They achieve excellent segmentation accuracy but lack inference speed. Therefore, we propose a backbone network SCDNet with a dual path structure and higher speed and accuracy. Firstly, we propose a split connection structure, which is a streamlined lightweight backbone with a parallel structure to increase inference speed. Secondly, we introduce a flexible dilated convolution using different dilation rates so that the network can have richer receptive fields to perceive objects. Then, we propose a three-level hierarchical module to effectively balance the feature maps with multiple resolutions. Finally, a refined flexible and lightweight decoder is utilized. Our work achieves a trade-off of accuracy and speed on the Cityscapes and Camvid datasets. Specifically, we obtain a 36% improvement in FPS and a 0.7% improvement in mIoU on the Cityscapes test set.

A Comparative Study of PP-LiteSeg, Dual Attention Network, DeeplabV3p and Asymmetric Neural Network for Rooftop Detection in UAV Images

“…This study investigate of deep learning-based rooftop detection using semantic segmentation [3,4] models such as (ANN), (DANet), PP-LiteSeg, and Deeplab3p. The reason using this four model was determined by the performance, strength to identify rooftop detection .…”