FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation (2021-09-02T00:00:00.000000Z)

TL;DR

This article proposes a Fast Bilateral Symmetrical Network (FBSNet), a symmetrical encoder-decoder structure with two branches, semantic information branch and spatial detail branch that can strike a good balance between accuracy and efficiency.

Abstract

Real-time semantic segmentation, which can be visually understood as the pixel-level classification task on the input image, currently has broad application prospects, especially in the fast-developing fields of autonomous driving and drone navigation. However, the huge burden of calculation together with redundant parameters are still the obstacles to its technological development. In this article, we propose a Fast Bilateral Symmetrical Network (FBSNet) to alleviate the above challenges. Specifically, FBSNet employs a symmetrical encoder-decoder structure with two branches, semantic information branch and spatial detail branch. The Semantic Information Branch (SIB) is the main branch with semantic architecture to acquire the contextual information of the input image and meanwhile acquire sufficient receptive field. While the Spatial Detail Branch (SDB) is a shallow and simple network used to establish local dependencies of each pixel for preserving details, which is essential for restoring the original resolution during the decoding phase. Meanwhile, a Feature Aggregation Module (FAM) is designed to effectively combine the output of these two branches. Experimental results of Cityscapes and CamVid show that the proposed FBSNet can strike a good balance between accuracy and efficiency. Specifically, it obtains 70.9% and 68.9% mIoU along with the inference speed of 90 fps and 120 fps on these two test datasets, respectively, with only 0.62 million parameters on a single RTX 2080Ti GPU. The code is available at https://github.com/IVIPLab/FBSNet.

Authors

Jian Yang

7 papers

Yi Yu

3 papers

Guangwei Gao

1 papers

TL;DR

Abstract

Authors

References64 items

NDNet: Narrow While Deep Network for Real-Time Semantic Segmentation

Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition

MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation

Coordinate Attention for Efficient Mobile Network Design

Constructing multilayer locality-constrained matrix regression framework for noise robust face super-resolution

Using Channel-Wise Attention for Deep CNN Based Real-Time Semantic Segmentation With Class-Aware Edge Information

Bi-direction Context Propagation Network for Real-time Semantic Segmentation

BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation

ADSCNet: asymmetric depthwise separable convolution for semantic segmentation in real-time

FDDWNet: A Lightweight Convolutional Neural Network for Real-Time Semantic Segmentation

ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks

DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation

Lednet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation

Searching for MobileNetV3

DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation

Fast-SCNN: Fast Semantic Segmentation Network

Fast Semantic Segmentation for Scene Perception

ESPNetv2: A Light-Weight, Power Efficient, and General Purpose Convolutional Neural Network

CCNet: Criss-Cross Attention for Semantic Segmentation

CGNet: A Light-Weight Context Guided Network for Semantic Segmentation

Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation

Dual Attention Network for Scene Segmentation

BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

CBAM: Convolutional Block Attention Module

DenseASPP for Semantic Segmentation in Street Scenes

Learning a Discriminative Feature Network for Semantic Segmentation

ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation

MobileNetV2: Inverted Residuals and Linear Bottlenecks

Non-local Neural Networks

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

Rethinking Atrous Convolution for Semantic Image Segmentation

Learning robust and discriminative low-rank representations for face recognition with occlusion

ICNet for Real-Time Semantic Segmentation on High-Resolution Images

Image Piece Learning for Weakly Supervised Semantic Segmentation

Pyramid Scene Parsing Network

Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes

Speeding up Semantic Segmentation for Autonomous Driving

Xception: Deep Learning with Depthwise Separable Convolutions

ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

Deep Residual Learning for Image Recognition

Rethinking the Inception Architecture for Computer Vision

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

ParseNet: Looking Wider to See Better

U-Net: Convolutional Networks for Biomedical Image Segmentation

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Fully convolutional networks for semantic segmentation

Very Deep Convolutional Networks for Large-Scale Image Recognition

ImageNet classification with deep convolutional neural networks

Rectified Linear Units Improve Restricted Boltzmann Machines

Professor

received the Ph.D. degree in Computer Science and from East China Normal University, Shanghai, China,

ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic Segmentation

were in the top winners (out of 29 teams) from ACM SIGSPATIAL GIS Cup 2013, and the Best Paper Runner-Up in APWeb-WAIM 2017, recognized as ﬁnalist of the World’s FIRST 10K

FIRST 10 K Best Paper Award

He is currently a Postdoctoral Fellow at the Center for Mathematical Artificial Intelligence, The Chinese University of Hong Kong. His main research interests includes image restoration

and FPD) with the Kyushu Institute of Technology. He is currently an Assistant Professor with the Kyushu Institute of Technology and an Excellent Young Researcher of MEXT-Japan

Institute of Technology and an Excellent Young Researcher of MEXT-Japan interests include computer vision, robotics, artiﬁcial intelligence observing

His research interests include image semantic segmentation

RANSACTIONS ON N EURAL N L EARNING

Her main research interests include learning and deep learning for multimedia understanding and knowledge discovery

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names