...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE Transactions on Pattern Analysis and Machine Intelligence >Deep Mixture of Diverse Experts for Large-Scale Visual Recognition
【24h】

Deep Mixture of Diverse Experts for Large-Scale Visual Recognition

机译：用于大规模视觉识别的多元专家深层混合

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

In this paper, a deep mixture of diverse experts algorithm is developed to achieve more efficient learning of a huge (mixture) network for large-scale visual recognition application. First, a two-layer ontology is constructed to assign large numbers of atomic object classes into a set of task groups according to the similarities of their learning complexities, where certain degrees of inter-group task overlapping are allowed to enable sufficient inter-group message passing. Second, one particular base deep CNNs with M + 1 outputs is learned for each task group to recognize its M atomic object classes and identify one special class of "not-in-group", where the network structure (numbers of layers and units in each layer) of the well-designed deep CNNs (such as AlexNet, VGG, GoogleNet, ResNet) is directly used to configure such base deep CNNs. For enhancing the separability of the atomic object classes in the same task group, two approaches are developed to learn more discriminative base deep CNNs: (a) our deep multi-task learning algorithm that can effectively exploit the inter-class visual similarities; (b) our two-layer network cascade approach that can improve the accuracy rates for the hard object classes at certain degrees while effectively maintaining the high accuracy rates for the easy ones. Finally, all these complementary base deep CNNs with diverse but overlapped outputs are seamlessly combined to generate a mixture network with larger outputs for recognizing tens of thousands of atomic object classes. Our experimental results have demonstrated that our deep mixture of diverse experts algorithm can achieve very competitive results on large-scale visual recognition.
机译：在本文中，开发了一种深入的不同专家算法的混合，实现了对大型视觉识别应用的巨大（混合）网络的更有效学习。首先，构造双层本体，以根据其学习复杂性的相似性为一组任务组分配大量原子对象类，其中允许允许某些组间任务重叠进行足够的组间消息通过。其次，为每个任务组学习具有M + 1输出的一个特定基础深度CNN，以识别其M原子对象类并识别一个特殊类别的“Not-In-oc-group”，其中网络结构（层数和单位数每个层）的良好设计的深CNN（例如AlexNet，VGG，Googlenet，Reset）直接用于配置此类基本深CNN。为了提高同一任务组中的原子对象类的可分离性，开发了两种方法来了解更多的判别基础CNN：（a）我们可以有效利用级别的视觉相似性的深度多任务学习算法; （b）我们的双层网络级联方法，可以提高某些程度的硬对象类的精度率，同时有效地保持易于的高精度率。最后，所有这些具有多样化但重叠输出的互补基础深度CNN无缝地组合以产生具有更大输出的混合网络，用于识别成千上万的原子对象类。我们的实验结果表明，我们对各种专家算法的深度混合可以在大规模视觉识别方面实现非常竞争力的结果。

著录项

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