首页|复杂场景下自适应注意力机制融合实时语义分割

复杂场景下自适应注意力机制融合实时语义分割

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
实现高准确度和低计算负担是卷积神经网络(CNN)实时语义分割面临的严峻挑战.针对复杂城市街道场景目标种类众多、光照变化大等特点,该文设计了一种高效的实时语义分割自适应注意力机制融合网络(AAFNet)分别提取图像空间细节和语义信息,再经过特征融合网络(FFN)获得准确语义图像.AAFNet采用扩展的深度可分离卷积(DDW)可增大语义特征提取感受野,提出自适应平均池化(Avp)和自适应最大池化(Amp)构成自适应注意力机制融合模块(AAFM),可细化目标边缘分割效果并降低小目标的漏分率.最后在复杂城市街道场景Cityscapes和CamVid数据集上分别进行了语义分割实验,所设计的AAFNet以32帧/s(Cityscapes)和52帧/s(CamVid)的推理速度获得73.0%和69.8%的平均分割精度(mIoU),且与扩展的空间注意力网络(DSANet)、多尺度上下文融合网络(MSCFNet)以及轻量级双边非对称残差网络(LBARNet)相比,AAFNet平均分割精度最高.
Adaptive Attention Mechanism Fusion for Real-Time Semantic Segmentation in Complex Scenes
Realizing high accuracy and low computational burden is a serious challenge faced by Convolutional Neural Network(CNN)for real-time semantic segmentation.In this paper,an efficient real-time semantic segmentation Adaptive Attention mechanism Fusion Network(AAFNet)is designed for complex urban street scenes with numerous types of targets and large changes in lighting.Image spatial details and semantic information are respectively extracted by the network,and then,through Feature Fusion Network(FFN),accurate semantic images are obtained.Dilated Deep-Wise separable convolution(DDW)is adopted by AAFNet to increase the receptive field of semantic feature extraction,an Adaptive Attention mechanism Fusion Module(AAFM)is proposed,which combines Adaptive average pooling(Avp)and Adaptive max pooling(Amp)to refine the edge segmentation effect of the target and reduce the leakage rate of small targets.Finally,semantic segmentation experiments are performed on the Cityscapes and CamVid datasets for complex urban street scenes.The designed AAFNet achieves 73.0%and 69.8%mean Intersection over Union(mIoU)at inference speeds of 32 fps(Cityscapes)and 52 fps(CamVid).Compared with Dilated Spatial Attention Network(DSANet),Multi-Scale Context Fusion Network(MSCFNet),and Lightweight Bilateral Asymmetric Residual Network(LBARNet),AAFNet has the highest segmentation accuracy.

Convolution Neural Network(CNN)Complex urban street scenesDilated depth-wise separable convolutionAdaptive attention mechanism fusionSegmentation accuracy

陈丹、刘乐、王晨昊、白熙茹、王子晨

展开 >

西安理工大学自动化与信息工程学院 西安 710048

陕西职业技术学院电子信息工程学院 西安 710038

卷积神经网络 复杂城市街道场景 扩展的深度可分离卷积 自适应注意力机制融合 分割精度

榆林市科技局计划项目西安市秦创原重点产业链核心技术攻关项目

2019-14623ZDCYJSGG0021-2023

2024

10.11999/JEIT231338

电子与信息学报
中国科学院电子学研究所 国家自然科学基金委员会信息科学部

电子与信息学报

CSTPCD北大核心
影响因子：1.302
ISSN：1009-5896
年,卷(期)：2024.46(8)