arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.00809cs.LGcs.CV
收藏

大型深度网络的自适应分层分解

Adaptive Hierarchical Decomposition of Large Deep Networks

Rochester Institute of Technology(罗切斯特理工学院)

Sumanth Chennupati, Sai Nooka, Shagan Sah, Raymond W Ptucha

摘要:

深度学习最近证明了它在视觉对象识别方面与人脑相媲美的能力。随着数据集变得越来越大,一个自然的问题是,现有的深度学习架构是否可以扩展到处理被认为是典型人类可感知的50 K以上的类。大多数深度学习架构专注于拆分不同的类别,而忽略了它们之间的相似性。本文介绍了一个框架,该框架可以自动分析和配置一系列较小的深度网络,以替代单一的大型网络。类的相似性指导创建一个家庭从课程到罚款分类器,解决分类问题更有效地比一个单一的大型分类器。由此产生的较小的网络是高度可扩展的,并行的,更实用的训练,并实现更高的分类精度。本文还提出了一种方法来自适应地选择配置的分层家庭的分类器使用链接统计从整体和子分类混淆矩阵。根据类的数量和问题的复杂度,选择深度学习模型并确定复杂度。大量的实验网络类,层和架构配置验证我们的结果。

英文摘要:

Deep learning has recently demonstrated its ability to rival the human brain for visual object recognition. As datasets get larger, a natural question to ask is if existing deep learning architectures can be extended to handle the 50+K classes thought to be perceptible by a typical human. Most deep learning architectures concentrate on splitting diverse categories, while ignoring the similarities amongst them. This paper introduces a framework that automatically analyzes and configures a family of smaller deep networks as a replacement to a singular, larger network. Class similarities guide the creation of a family from course to fine classifiers which solve categorical problems more effectively than a single large classifier. The resulting smaller networks are highly scalable, parallel and more practical to train, and achieve higher classification accuracy. This paper also proposes a method to adaptively select the configuration of the hierarchical family of classifiers using linkage statistics from overall and sub-classification confusion matrices. Depending on the number of classes and the complexity of the problem, a deep learning model is selected and the complexity is determined. Numerous experiments on network classes, layers, and architecture configurations validate our results.

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。

↑