...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>IEEE transactions on multimedia >Multi-Scale Interpretation Model for Convolutional Neural Networks: Building Trust Based on Hierarchical Interpretation
【24h】

Multi-Scale Interpretation Model for Convolutional Neural Networks: Building Trust Based on Hierarchical Interpretation

机译：卷积神经网络的多尺度解释模型：基于分层解释的信任建立

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

With the rapid development of deep learning models, their performances in various tasks have improved; meanwhile, their increasingly intricate architectures make them difficult to interpret. To tackle this challenge, model interpretability is essential and has been investigated in a wide range of applications. For end users, model interpretability can he used to build trust in the deployed machine learning models. For practitioners, interpretability plays a critical role in model explanation, model validation, and model improvement to develop a faithful model. In this paper, we propose a novel Multi-scale Interpretation (MINT) model for convolutional neural networks using both the perturbation-based and the gradient-based interpretation approaches. It learns the class-discriminative interpretable knowledge from the multi-scale perturbation of feature information in different layers of deep networks. The proposed MINT model provides the coarse-scale and the fine-scale interpretations for the attention in the deep layer and specific features in the shallow layer, respectively. Experimental results show that the MINT model presents the class-discriminative interpretation of the network decision and explains the significance of the hierarchical network structure.
机译：随着深度学习模型的快速发展，它们在各种任务中的表现得到了提高。同时，它们越来越复杂的体系结构使它们难以解释。为了应对这一挑战，模型的可解释性至关重要，并且已经在广泛的应用中进行了研究。对于最终用户，他可以使用模型的可解释性来建立对已部署的机器学习模型的信任。对于从业者而言，可解释性在模型解释，模型验证和模型改进以建立忠实模型方面起着至关重要的作用。在本文中，我们使用基于扰动和基于梯度的解释方法，为卷积神经网络提出了一种新颖的多尺度解释（MINT）模型。它从深度网络的不同层中的特征信息的多尺度扰动中学习了可区分类的可解释知识。提出的MINT模型分别为深层的关注点和浅层的特定特征提供了粗尺度和精细尺度的解释。实验结果表明，MINT模型提供了网络决策的类判别解释，并解释了分层网络结构的重要性。

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