ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Differentiated Explanation of Deep Neural Networks With Skewed Distributions

Fu, Weijie; Wang, Meng*; Du, Mengnan; Liu, Ninghao; Hao, Shijie; Hu, Xia
IEEE Transactions on Pattern Analysis and Machine Intelligence2022-6-1DOI: 10.1109/TPAMI.2021.3049784
1被引4阅读
引用收藏
分享

摘要

Over the last decade, deep neural networks (DNNs) are regarded as black-box methods, and their decisions are criticized for the lack of explainability. Existing attempts based on local explanations offer each input a visual saliency map, where the supporting features that contribute to the decision are emphasized with high relevance scores. In this paper, we improve the saliency map based on differentiated explanations, of which the saliency map not only distinguishes the supporting features from backgrounds but also shows the different degrees of importance of the various parts within the supporting features. To do this, we propose to learn a differentiated relevance estimator called DRE, where a carefully-designed distribution controller is introduced to guide the relevance scores towards right-skewed distributions. DRE can be directly optimized under pure classification losses, enabling higher faithfulness of explanations and avoiding non-trivial hyper-parameter tuning. The experimental results on three real-world datasets demonstrate that our differentiated explanations significantly improve the faithfulness with high explainability. Our code and trained models are available at https://github.com/fuweijie/DRE.

学科与关键词

关键词
GeneratorsPerturbation methodsTuningNeural networksConvolutionVisualizationTrainingDeep neural networkslocal explanationrelevance scoresdifferentiated saliency maps
相关
加载中…
  • A review and benchmark of feature importance methods for neural networks
    Mandler, Hannes*; Weigand, BernhardACM Computing Surveys, 2024, 56(12): 318.
  • Rethinking Attention-Model Explainability through Faithfulness Violation Test
    Liu, Yibing; Li, Haoliang*; Guo, Yangyang; Kong, Chenqi; Li, Jing; Wang, Shiqi38th International Conference on Machine Learning (ICML), Baltimore, MD, 2022-07-17 To 2022-07-23.
  • Explainable AI: A review of applications to neuroimaging data
    Farahani, Farzad V.*; Fiok, Krzysztof; Lahijanian, Behshad; Karwowski, Waldemar; Douglas, Pamela K.Frontiers in Neuroscience, 2022, 16: 906290.被引 16
查看全部 →

发表信息

论文状态
公开发表
期刊
IEEE Transactions on Pattern Analysis and Machine Intelligence
发表日期
2022-06-01
卷期
第 44 卷, 第 6 期
页码
2909-2922
DOI
10.1109/TPAMI.2021.3049784
语言
ENGLISH
期刊等级
1区
成果收录
SCIE
资助标注
National Nature Science Foundation of China [61725203, 62020106007, 61772171]; Fundamental Research Funds for the Central Universities [PA2020GDKC0023, PA2019GDZC0095]; China Scholarship Council

作者

  • F

    Fu, Weijie (第一作者)

  • W

    Wang, Meng (通讯)

查看全部 6 位作者收起作者
  • D

    Du, Mengnan

  • L

    Liu, Ninghao

  • H

    Hao, Shijie

  • H

    Hu, Xia

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417