利用可解释性:基于概念的深度神经网络行人检测

P. Feifel, Frank Bonarens, F. Köster
{"title":"利用可解释性:基于概念的深度神经网络行人检测","authors":"P. Feifel, Frank Bonarens, F. Köster","doi":"10.1145/3488904.3493379","DOIUrl":null,"url":null,"abstract":"The automation of driving systems relies on proof of the correct functioning of perception. Arguing the safety of deep neural networks (DNNs) must involve quantifiable evidence. Currently, the application of DNNs suffers from an incomprehensible behavior. It is still an open question if post-hoc methods mitigate the safety concerns of trained DNNs. Our work proposes a method for inherently interpretable and concept-based pedestrian detection (CPD). CPD explicitly structures the latent space with concept vectors that learn features for body parts as predefined concepts. The distance-based clustering and separation of latent representations build an interpretable reasoning process. Hence, CPD predicts a body part segmentation based on distances of latent representations to concept vectors. A non-interpretable 2d bounding box prediction for pedestrians complements the segmentation. The proposed CPD generates additional information that can be of great value in a safety argumentation of a DNN for pedestrian detection. We report competitive performance for the task of pedestrian detection. Finally, CPD enables concept-based tests to quantify evidence of a safe perception in automated driving systems.","PeriodicalId":332312,"journal":{"name":"Proceedings of the 5th ACM Computer Science in Cars Symposium","volume":"109 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Leveraging Interpretability: Concept-based Pedestrian Detection with Deep Neural Networks\",\"authors\":\"P. Feifel, Frank Bonarens, F. Köster\",\"doi\":\"10.1145/3488904.3493379\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The automation of driving systems relies on proof of the correct functioning of perception. Arguing the safety of deep neural networks (DNNs) must involve quantifiable evidence. Currently, the application of DNNs suffers from an incomprehensible behavior. It is still an open question if post-hoc methods mitigate the safety concerns of trained DNNs. Our work proposes a method for inherently interpretable and concept-based pedestrian detection (CPD). CPD explicitly structures the latent space with concept vectors that learn features for body parts as predefined concepts. The distance-based clustering and separation of latent representations build an interpretable reasoning process. Hence, CPD predicts a body part segmentation based on distances of latent representations to concept vectors. A non-interpretable 2d bounding box prediction for pedestrians complements the segmentation. The proposed CPD generates additional information that can be of great value in a safety argumentation of a DNN for pedestrian detection. We report competitive performance for the task of pedestrian detection. Finally, CPD enables concept-based tests to quantify evidence of a safe perception in automated driving systems.\",\"PeriodicalId\":332312,\"journal\":{\"name\":\"Proceedings of the 5th ACM Computer Science in Cars Symposium\",\"volume\":\"109 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-11-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 5th ACM Computer Science in Cars Symposium\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3488904.3493379\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 5th ACM Computer Science in Cars Symposium","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3488904.3493379","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

驾驶系统的自动化依赖于对感知功能正确运作的证明。论证深度神经网络(dnn)的安全性必须包含可量化的证据。目前,深度神经网络的应用存在一种不可理解的行为。这仍然是一个悬而未决的问题,如果事后方法减轻安全问题的训练dnn。我们的工作提出了一种固有可解释和基于概念的行人检测(CPD)方法。CPD明确地用概念向量来构建潜在空间,这些概念向量学习身体部位的特征作为预定义的概念。基于距离的聚类和潜在表征的分离构建了一个可解释的推理过程。因此,CPD基于潜在表示到概念向量的距离来预测身体部位分割。行人不可解释的2d边界框预测补充了分割。建议的CPD产生额外的信息,这些信息在深度神经网络用于行人检测的安全论证中具有很大的价值。我们报告了行人检测任务的竞争性表现。最后,CPD使基于概念的测试能够量化自动驾驶系统中安全感知的证据。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Leveraging Interpretability: Concept-based Pedestrian Detection with Deep Neural Networks
The automation of driving systems relies on proof of the correct functioning of perception. Arguing the safety of deep neural networks (DNNs) must involve quantifiable evidence. Currently, the application of DNNs suffers from an incomprehensible behavior. It is still an open question if post-hoc methods mitigate the safety concerns of trained DNNs. Our work proposes a method for inherently interpretable and concept-based pedestrian detection (CPD). CPD explicitly structures the latent space with concept vectors that learn features for body parts as predefined concepts. The distance-based clustering and separation of latent representations build an interpretable reasoning process. Hence, CPD predicts a body part segmentation based on distances of latent representations to concept vectors. A non-interpretable 2d bounding box prediction for pedestrians complements the segmentation. The proposed CPD generates additional information that can be of great value in a safety argumentation of a DNN for pedestrian detection. We report competitive performance for the task of pedestrian detection. Finally, CPD enables concept-based tests to quantify evidence of a safe perception in automated driving systems.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信