arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.01767cs.LGcs.CVeess.IVeess.SP
收藏

深度学习分类中嵌入空间的比较

Comparison of Embedded Spaces for Deep Learning Classification

Panoradio(全景无线电)

Stefan Scholl

AI总结:

本文比较了用于分类嵌入空间设计的不同损失函数与网络参数约束,并在 MNIST、Fashion MNIST 和 CIFAR-10 上以二维、三维嵌入展示其几何结构差异。

摘要:

嵌入空间是深度学习的关键特征。良好的嵌入空间能很好地表示数据,以支持分类以及开集识别、小样本学习和可解释性等先进技术。本文简要概述了为分类设计嵌入空间的不同技术。它就嵌入空间可实现的几何结构,比较了不同的损失函数和网络参数约束。这些技术通过 MNIST、Fashion MNIST 和 CIFAR-10 数据集的二维和三维嵌入进行演示,从而可以对嵌入空间进行可视化检查。

英文摘要:

Embedded spaces are a key feature in deep learning. Good embedded spaces represent the data well to support classification and advanced techniques such as open-set recognition, few-short learning and explainability. This paper presents a compact overview of different techniques to design embedded spaces for classification. It compares different loss functions and constraints on the network parameters with respect to the achievable geometric structure of the embedded space. The techniques are demonstrated with two and three-dimensional embeddings for the MNIST, Fashion MNIST and CIFAR-10 datasets, allowing visual inspection of the embedded spaces.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑