Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Thymosin Alpha-1 Restores Chemotherapy-Induced Antitumor Immunity by Chaperoning a MicroRNA Ligand of TLR7 in Dendritic Cells.

Cancer research·2026
Same author

PMF-YOLO: a parameter-efficient multi-scale detector for underwater optical imagery under scattering and nonuniform illumination.

Applied optics·2026
Same author

Dual-branch underwater image enhancement network based on fusion of polarization and color information.

Applied optics·2026
Same author

The Expression of ABC and MFS Transporter Genes, Not Mutations at <i>ScCyp51</i>, Is Associated with Difenoconazole Resistance in <i>Stagonosporopsis Cucurbitacearum</i> from Melon Fields.

Journal of agricultural and food chemistry·2026
Same author

Policy-Guided Model Predictive Path Integral for Safe Manipulator Trajectory Planning.

Sensors (Basel, Switzerland)·2026
Same author

Polarization-guided diffusion model for physically inspired underwater image descattering.

Applied optics·2026

相关实验视频

Updated: Jul 11, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

564

轻量级的语义细分网络,具有可配置的上下文和小对象注意力.

Chunyu Zhang1, Fang Xu2, Chengdong Wu1

  • 1Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China.

Frontiers in computational neuroscience
|November 8, 2023
PubMed
概括

本研究介绍了CCSONet,一个轻量级的语义细分网络,用于解决特征扭曲和小对象丢失. 它实现了高精度和速度,超越现有方法.

关键词:
文本功能增强 文本功能增强 文本功能增强编码器解码器编码器轻量级网络轻量级的网络.语义细分 语义细分 语义细分 语义细分小物体注意力 小物体注意力

更多相关视频

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

435
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

相关实验视频

Last Updated: Jul 11, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

564
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

435
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

科学领域:

  • 计算机视觉 计算机视觉
  • 深度学习 (Deep Learning) 是一种深度学习.
  • 图像细分 图像细分

背景情况:

  • 当前的语义细分算法在编码特征扭曲和丢失小对象细节方面扎.
  • 现有的上下文信息交换方法具有固定的空间范围,限制了它们的有效性.
  • 高分辨率功能维护有助于检测小物体,但会降低网络速度.

研究的目的:

  • 提出一个新的轻量级语义细分网络,CCSONet,旨在克服现有方法的局限性.
  • 通过结合可配置的上下文和注意力机制来增强小物体的特征表示.
  • 为了提高语义细分任务的准确性和效率.

主要方法:

  • 开发了一个名为CCSONet的轻量级语义细分网络.
  • 引入了一个长短距离可配置上下文特征增强模块 (LSCFEM),用于灵活的空间上下文.
  • 实现了一个小物体注意力解码模块 (SOADM),以关注和增强小物体特征.

主要成果:

  • 在Cityscapes数据集上,CCSONet实现了7690万U,在Camvid数据集上实现了7310万U.
  • 该网络在Cityscapes和Camvid上保持了高运行速度,分别为87 FPS和138 FPS.
  • 与其他轻量级语义细分算法相比,CCSONet的准确性更高.

结论:

  • CCSONet有效地解决了语义细分中的特征扭曲和小对象丢失.
  • 拟议的LSCFEM和SOADM模块提供可配置的环境和有针对性的注意力,以提高性能.
  • CCSONet为高效准确的轻量级语义细分提供了一个有前途的解决方案.