使用分离指数进行语义细分的编码器-解码器模型的有效压缩
Movahed Jamshidi1, Ahmad Kalhor2, Abdol-Hossein Vahabie2
1School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran. mo.jamshidi@ut.ac.ir.
Scientific reports
|July 9, 2025
概括
本研究介绍了一种新的压缩方法,用于使用分离指数 (SI) 的语义细分模型. 这种技术显著降低了模型大小和计算成本,同时保持或提高了细分精度.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 深度学习 (Deep Learning) 是一种深度学习.
背景情况:
- 编码-解码架构对于语义细分至关重要,但通常会受到高计算复杂性的困扰.
- 保持细粒度的空间细节对于准确的细分至关重要,这对模型压缩构成了挑战.
研究的目的:
- 在语义细分中开发和评估用于编码器-解码器网络的新型压缩方法.
- 利用分离指数 (SI) 识别和修剪多余的网络组件.
主要方法:
- 利用分离指数 (SI) 来量化像素级别的类分离的特征地图区分能力.
- 实施了针对各种语义细分架构中的多余层和过器的修剪策略.
- 评估了各种数据集 (CamVid,KiTS19,数据科学碗,空中影像,MVTec AD) 和架构 (U-Net,LinkNet,MobileNet,DeepLabV3,SegNet) 的方法.
主要成果:
- 通过SI驱动的压缩实现了模型参数和浮点运算的显著减少 (高达70%).
- 在所有测试的数据集和架构中保持或改进了细分精度,用平均交叉点在欧盟 (IoU) 来衡量.
- 展示了一个压缩的DeepLabV3模型,在空中图像上将平均IOU从0.624提高到0.638,参数减少2.6倍,推断速度更快.
结论:
- 基于SI的修剪提供了一种有效的方法来平衡语义细分中的模型效率和性能.
- 拟议的方法为在资源有限的环境中部署深度学习模型提供了实际解决方案.
- 这项工作突出了特征分离度量的潜力,以指导高效的深度学习模型压缩.
相关概念视频
01:18Reducing Line Loss
196
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
196
01:14Extraction: Partition and Distribution Coefficients
3.0K
The distribution law or Nernst's distribution law is the law that governs the distribution of a solute between two immiscible solvents. This law, also known as the partition law, states that if a solute is added to the mixture of two immiscible solvents at a constant temperature, the solute is distributed between the two solvents in such a way that the ratio of solute concentrations in the solvents remains constant at equilibrium.
For extracting a solute from an aqueous phase into an...
For extracting a solute from an aqueous phase into an...
3.0K
00:56Extraction: Advanced Methods
545
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is...
545
01:29Aggregates Classification
387
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
387