...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Quality Control, Transactions >Dense Aggregation Based Efficient Network for Image Semantic Segmentation in Edge Intelligent Tasks
【24h】

Dense Aggregation Based Efficient Network for Image Semantic Segmentation in Edge Intelligent Tasks

机译：基于致密的聚合在Edge智能任务中的图像语义分割有效网络

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The image semantic segmentation algorithm required by edge intelligence needs to have high accuracy and real-time performance at the same time. In this paper, a new image segmentation network: Dense Aggregation based efficient neural network (DA-ENet) is proposed. The proposed network aggregates feature maps of each two adjacent stages of DA-ENet into an aggregation feature map, and uses shortcut connections connect each encoder stage feature map to the two decoder stages. In DA-Enet the linear propagation way of original ENet was changed. DA-Enet uses aggregations to realize feature fusion at different stages of the network and reduce the number of network parameters. DA-Enet uses shortcut connections to enhance the propagation and reuse of features. Aggregations and shortcut connections make DA-ENet a densely connected network. In densely connected network, each layer receives additional supervision from the loss function. Therefore, DA-Enet will be easier to train and has higher accuracy.The proposed DA-ENet was evaluated on three standard datasets: CamVid, CityScapes and SUN RGB-D. The experimental results demonstrate that DA-ENet has similar inference speed but higher segmentation accuracy to ENet.
机译：边缘智能所需的图像语义分段算法需要同时具有高精度和实时性能。在本文中，提出了一种新的图像分割网络：提出了基于密集的聚合的高效神经网络（DA-ENET）。所提出的网络聚合DA-ENET的每个相邻阶段的特征映射到聚合特征映射，并使用快捷方式连接每个编码器级特征映射到两个解码器级。在DA-ENET中，原始eNET的线性传播方式改变。 DA-ENET使用聚合实现网络的不同阶段的特征融合，并减少网络参数的数量。 DA-ENET使用快捷连接来增强功能的传播和重用。聚合和快捷方式连接使DA-ENET连接密集的网络。在密集连接的网络中，每个层从损耗函数接收额外的监督。因此，DA-ENET将更容易训练并具有更高的精度。建议的DA-ENET在三个标准数据集中进行了评估：Camvid，CityOcapes和Sun RGB-D。实验结果表明，DA-ENET具有类似的推广速度，但eNET的分割精度较高。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号