Details

Autor(en) / Beteiligte

• Yu, Changqian
• Wang, Jingbo
• Peng, Chao
• Gao, Changxin
• Yu, Gang
• Sang, Nong

Titel

BiSeNet: Bilateral Segmentation Network for Real-Time Semantic Segmentation

Ist Teil von

• Computer Vision – ECCV 2018, p.334-349

Ort / Verlag

Cham: Springer International Publishing

Link zum Volltext

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• Semantic segmentation requires both rich spatial information and sizeable receptive field. However, modern approaches usually compromise spatial resolution to achieve real-time inference speed, which leads to poor performance. In this paper, we address this dilemma with a novel Bilateral Segmentation Network (BiSeNet). We first design a Spatial Path with a small stride to preserve the spatial information and generate high-resolution features. Meanwhile, a Context Path with a fast downsampling strategy is employed to obtain sufficient receptive field. On top of the two paths, we introduce a new Feature Fusion Module to combine features efficiently. The proposed architecture makes a right balance between the speed and segmentation performance on Cityscapes, CamVid, and COCO-Stuff datasets. Specifically, for a 2048 ×\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\times $$\end{document} 1024 input, we achieve 68.4% Mean IOU on the Cityscapes test dataset with speed of 105 FPS on one NVIDIA Titan XP card, which is significantly faster than the existing methods with comparable performance.