CGDFNet:一个双分支实时语义细分网络,具有上下文引导的细节融合
Shan Zhao1, Wenjing Fu2, Jiajia Gao1
1School of Software, Henan Polytechnic University, 2001 Century Avenue, Jiaozuo, 454000, China.
Scientific reports
|February 16, 2026
概括
一个新的上下文引导细节融合网络 (CGDFNet) 通过保留图像细节和增强上下文信息来改善实时语义细分. 这种新的方法有效地平衡了细分精度和高推断速度.
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:
- 双分支网络对于实时语义细分至关重要.
- 现有的方法在下方采样过程中遭受细节损失,并未充分利用上下文信息.
- 传统的融合方法难以有效地整合本地和全球特征.
研究的目的:
- 开发一个上下文导向的细节融合网络 (CGDFNet),以增强特征表示和细节保存在语义分割中.
- 解决现有的双分支网络在细节丢失和上下文信息未充分利用方面的局限性.
主要方法:
- 在上下文分支中实现了一个语义精细化模块 (SRM),用于适应性聚合和并行特征处理.
- 在细节分支中引入了上下文引导细节模块 (CGDM),以使用语义信息来加强高频特征.
- 开发了一个里埃-域自适应融合模块 (FDAFM),通过自适应关和里埃变换,高效地融合双分支特征.
主要成果:
- 在Cityscapes测试套件上,CGDFNet在87.6 FPS实现了77.8%的mIoU.
- 在CamVid测试套件中,CGDFNet在128.7 FPS的速度达到77.9%的mIoU.
- 实验结果表明,细分质量和实时推断速度之间存在平衡.
结论:
- 通过保留图像细节和利用上下文信息,CGDFNet有效地增强了特征表示.
- 拟议的网络在实时语义细分方面实现了最先进的性能.
- 对于在语义细分中需要准确性和速度的应用程序,CGDFNet提供了一个有前途的解决方案.
相关概念视频
01:04¹³C NMR: ¹H–¹³C Decoupling
1.7K
The probability of having two carbon-13 atoms next to each other is negligible because of the low natural abundance of carbon-13. Consequently, peak splitting due to carbon-carbon spin-spin coupling is not observed in spectra. However, protons up to three sigma bonds away split the carbon signal according to the n+1 rule, resulting in complicated spectra.
A broadband decoupling technique is used to simplify these complex, sometimes overlapping, signals. Broadband decoupling relies on a...
A broadband decoupling technique is used to simplify these complex, sometimes overlapping, signals. Broadband decoupling relies on a...
1.7K
01:20Structural Classification of Joints
8.0K
Joints, also known as articulations, are classified based on their structural characteristics, i.e., based on whether the articulating surfaces of the adjacent bones are directly connected by fibrous connective tissue or cartilage, or whether the articulating surfaces contact each other within a fluid-filled joint cavity. These differences serve to divide the joints of the body into three structural classifications.
A fibrous joint is where the adjacent bones are united by fibrous connective...
A fibrous joint is where the adjacent bones are united by fibrous connective...
8.0K
01:25Network Function of a Circuit
1.1K
Frequency response analysis in electrical circuits provides vital insights into a circuit's behavior as the frequency of the input signal changes. The transfer function, a mathematical tool, is instrumental in understanding this behavior. It defines the relationship between phasor output and input and comes in four types: voltage gain, current gain, transfer impedance, and transfer admittance. The critical components of the transfer function are the poles and zeros.
1.1K
01:16SFG Algebra
467
In Signal Flow Graph (SFG) algebra, the value a node represents is determined by the sum of all signals entering that node. This summed value is then transmitted through every branch leaving the node, making the SFG a powerful tool for visualizing and analyzing control systems.
Each node in an SFG corresponds to a variable, and the interactions between nodes are represented by branches with associated gains. When multiple branches lead into a node, the value at that node is the sum of the...
Each node in an SFG corresponds to a variable, and the interactions between nodes are represented by branches with associated gains. When multiple branches lead into a node, the value at that node is the sum of the...
467