相关实验视频

Updated: Jul 10, 2025

Quantifying Mixing using Magnetic Resonance Imaging

Quantifying Mixing using Magnetic Resonance Imaging

Published on: January 25, 2012

基于修改的MLP-Mixer的圆形印章的表示学习方法

Yuan Cao¹, You Zhou¹, Zhiwen Zhang¹

¹College of Information Science and Engineering, Hohai University, Changzhou 213022, China.

Entropy (Basel, Switzerland)

|November 24, 2023

概括

这项研究介绍了Stamp-MLP,一种新的海印记学习方法. 邮票-MLP在较少参数的密封面,产品类型和单个密封件的分类方面实现了卓越的准确性.

科学领域:

计算机视觉计算机视觉
机器学习机器学习
模式识别模式识别

背景情况:

密封印记分析对于认证和识别至关重要.
像MLP-Mixer,VGG16和ResNet50这样的现有方法在捕获细粒度细节方面存在局限性.
需要更高效,更准确的密封印记表示学习.

研究的目的:

提出 Stamp-MLP,一种增强的密封印记表示学习技术.
为了提高密封面,产品类型和单个密封的分类准确性.
与现有架构相比,开发具有更少参数和更好的性能的模型.

主要方法:

开发了基于MLP-Mixer的技术Stamp-MLP,使用循环密封重绘而不是补丁线性映射.
取代了平均聚合,以全球关注聚合为全面的信息提取.
采用了三个分类任务:密封面,产品类型和个别密封标识.

主要成果:

在密封面分类中,Stamp-MLP获得了最高的准确度 (89.61%),在较少的训练样本中超过了MLP-Mixer,VGG16和ResNet50.
在产品类型方面达到90.68%的卓越准确率,在密封印记分类方面达到91.96%.
以最少的参数 (2.67 M) 证明了最有效的模型.

结论:

邮票MLP在封印印记表示学习中提供了显著的进步.
与既有模型相比,拟议的方法提供了更高的准确性和效率.
循环海重绘和全球关注聚合是海分析的有效策略.

关键词:

这就是MLP-Mixer.代表性学习学习学习印章识别印章识别印章识别

更多相关视频

One-Step Approach to Fabricating Polydimethylsiloxane Microfluidic Channels of Different Geometric Sections by Sequential Wet Etching Processes

One-Step Approach to Fabricating Polydimethylsiloxane Microfluidic Channels of Different Geometric Sections by Sequential Wet Etching Processes

Published on: September 13, 2018

Author Spotlight: Integrating Computational and Experimental Approaches in Precision Oncology

Author Spotlight: Integrating Computational and Experimental Approaches in Precision Oncology

Published on: December 1, 2023

相关概念视频

Signal Flow Graphs

Signal Flow Graphs

Signal-flow graphs offer a streamlined and intuitive approach to representing control systems, providing an alternative to traditional block diagrams. These graphs use branches to symbolize systems and nodes to represent signals, effectively illustrating the relationships and interactions within the system.
In a signal-flow graph, branches denote the system's transfer functions, while nodes represent the signals. The direction of signal flow is indicated by arrows, with the corresponding...