• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文学位 >Fusion of Mini-Deep Nets.
【24h】

Fusion of Mini-Deep Nets.

机译：微型深网融合。

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Image classification and object recognition are some of the most prominent problems in computer vision. The difficult nature of finding objects regardless of pose and occlusions requires a large number of compute resources. Recent advancements in technology have made great strides towards solving this problem, and in particular, deep learning has revolutionized this field in the last few years.;The classification of large datasets, such as the popular ImageNet dataset, requires a network with millions of weights. Learning each of these weights using back propagation requires a compute intensive training phase with many training samples. Recent compute technology has proven adept at classifying 1000 classes, but it is not clear if computers will be able to differentiate and classify the more than 40,000 classes humans are capable of doing. The goal of this thesis is to train computers to attain human-like performance on large-class datasets. Specifically, we introduce two types of hierarchical architectures: Late Fusion and Early Fusion. These architectures will be used to classify datasets with up to 1000 objects, while simultaneously reducing both the number of computations and training time. These hierarchical architectures maintain discriminative relationships amongst networks within each layer as well as an abstract relationship from one layer to the next. The resulting framework reduces the individual network sizes, and thus the total number of parameters that need to be learned. The smaller number of parameters results in decreased training time.
机译：图像分类和对象识别是计算机视觉中最突出的问题。无论姿势和遮挡如何都很难找到对象，这需要大量的计算资源。最新的技术进步已在解决该问题上取得了长足的进步，尤其是在过去的几年中，深度学习使这一领域发生了革命性的变化。大型数据集的分类（例如流行的ImageNet数据集）需要具有数百万权重的网络。使用反向传播学习这些权重中的每一个都需要具有大量训练样本的计算密集型训练阶段。事实证明，最新的计算机技术擅长于对1000个类别进行分类，但是尚不清楚计算机是否能够区分和分类人类能够完成的40,000多个类别。本文的目的是训练计算机在大型数据集上达到类似人的性能。具体来说，我们介绍两种类型的层次结构：晚期融合和早期融合。这些架构将用于对多达1000个对象的数据集进行分类，同时减少计算数量和训练时间。这些分层体系结构维护每一层内网络之间的区分关系以及从一层到另一层的抽象关系。结果框架减少了单个网络的大小，从而减少了需要学习的参数总数。参数数量越少，训练时间就越短。

著录项

  • 作者

    Nooka, Sai Prasad.;

  • 作者单位

    Rochester Institute of Technology.;

  • 授予单位 Rochester Institute of Technology.;
  • 学科 Computer engineering.
  • 学位 M.S.
  • 年度 2016
  • 页码 93 p.
  • 总页数 93
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 公共建筑;
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号