BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

Abstract

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 2048x1024 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.

arXiv commentAccepted to ECCV 2018. 17 pages, 4 figures, 9 tables

References in corpus (21)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Rethinking Atrous Convolution for Semantic Image Segmentation
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• Deep Residual Learning for Image Recognition
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Fully Convolutional Networks for Semantic Segmentation
• Squeeze-and-Excitation Networks
• ParseNet: Looking Wider to See Better
• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
• Recurrent Models of Visual Attention
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Learning Deconvolution Network for Semantic Segmentation
• Xception: Deep Learning with Depthwise Separable Convolutions
• Pyramid Scene Parsing Network
• ICNet for Real-Time Semantic Segmentation on High-Resolution Images
• Learning a Discriminative Feature Network for Semantic Segmentation
• High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks
• Real-time Semantic Image Segmentation via Spatial Sparsity
• Understanding Convolution for Semantic Segmentation

Cited by in corpus (3)

• UVid-Net: Enhanced Semantic Segmentation of UAV Aerial Videos by Embedding Temporal Information
• DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation
• 3D-DEEP: 3-Dimensional Deep-learning based on elevation patterns forroad scene interpretation