EVET:使用图像变换增强深度神经网络的视觉解释

Youngrock Oh, Hyungsik Jung, Jeonghyung Park, Min Soo Kim
{"title":"EVET:使用图像变换增强深度神经网络的视觉解释","authors":"Youngrock Oh, Hyungsik Jung, Jeonghyung Park, Min Soo Kim","doi":"10.1109/WACV48630.2021.00362","DOIUrl":null,"url":null,"abstract":"Numerous interpretability methods have been developed to visually explain the behavior of complex machine learning models by estimating parts of the input image that are critical for the model’s prediction. We propose a general pipeline of enhancing visual explanations using image transformations (EVET). EVET considers transformations of the original input image to refine the critical input region based on an intuitive rationale that the region estimated to be important in variously transformed inputs is more important. Our proposed EVET is applicable to existing visual explanation methods without modification. We validate the effectiveness of the proposed method qualitatively and quantitatively to show that the resulting explanation method outperforms the original in terms of faithfulness, localization, and stability. We also demonstrate that EVET can be used to achieve desirable performance with a low computational cost. For example, EVET-applied Grad-CAM achieves performance comparable to Score-CAM, which is the state-of-the-art activation-based explanation method, while reducing execution time by more than 90% on VOC, COCO, and ImageNet.","PeriodicalId":236300,"journal":{"name":"2021 IEEE Winter Conference on Applications of Computer Vision (WACV)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":"{\"title\":\"EVET: Enhancing Visual Explanations of Deep Neural Networks Using Image Transformations\",\"authors\":\"Youngrock Oh, Hyungsik Jung, Jeonghyung Park, Min Soo Kim\",\"doi\":\"10.1109/WACV48630.2021.00362\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Numerous interpretability methods have been developed to visually explain the behavior of complex machine learning models by estimating parts of the input image that are critical for the model’s prediction. We propose a general pipeline of enhancing visual explanations using image transformations (EVET). EVET considers transformations of the original input image to refine the critical input region based on an intuitive rationale that the region estimated to be important in variously transformed inputs is more important. Our proposed EVET is applicable to existing visual explanation methods without modification. We validate the effectiveness of the proposed method qualitatively and quantitatively to show that the resulting explanation method outperforms the original in terms of faithfulness, localization, and stability. We also demonstrate that EVET can be used to achieve desirable performance with a low computational cost. For example, EVET-applied Grad-CAM achieves performance comparable to Score-CAM, which is the state-of-the-art activation-based explanation method, while reducing execution time by more than 90% on VOC, COCO, and ImageNet.\",\"PeriodicalId\":236300,\"journal\":{\"name\":\"2021 IEEE Winter Conference on Applications of Computer Vision (WACV)\",\"volume\":\"34 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"10\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 IEEE Winter Conference on Applications of Computer Vision (WACV)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/WACV48630.2021.00362\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE Winter Conference on Applications of Computer Vision (WACV)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WACV48630.2021.00362","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 10

摘要

已经开发了许多可解释性方法,通过估计输入图像中对模型预测至关重要的部分来直观地解释复杂机器学习模型的行为。我们提出了一个使用图像变换(EVET)增强视觉解释的通用管道。EVET考虑原始输入图像的变换来细化关键输入区域,基于一个直观的原理,即在各种变换的输入中估计重要的区域更重要。我们提出的EVET无需修改即可适用于现有的视觉解释方法。我们定性和定量地验证了所提出方法的有效性,以表明所得到的解释方法在信度、局部化和稳定性方面优于原始方法。我们还证明了EVET可以用较低的计算成本获得理想的性能。例如,应用evet的Grad-CAM实现了与Score-CAM相当的性能,Score-CAM是最先进的基于激活的解释方法,同时在VOC, COCO和ImageNet上减少了90%以上的执行时间。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
EVET: Enhancing Visual Explanations of Deep Neural Networks Using Image Transformations
Numerous interpretability methods have been developed to visually explain the behavior of complex machine learning models by estimating parts of the input image that are critical for the model’s prediction. We propose a general pipeline of enhancing visual explanations using image transformations (EVET). EVET considers transformations of the original input image to refine the critical input region based on an intuitive rationale that the region estimated to be important in variously transformed inputs is more important. Our proposed EVET is applicable to existing visual explanation methods without modification. We validate the effectiveness of the proposed method qualitatively and quantitatively to show that the resulting explanation method outperforms the original in terms of faithfulness, localization, and stability. We also demonstrate that EVET can be used to achieve desirable performance with a low computational cost. For example, EVET-applied Grad-CAM achieves performance comparable to Score-CAM, which is the state-of-the-art activation-based explanation method, while reducing execution time by more than 90% on VOC, COCO, and ImageNet.
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:604180095
Book学术官方微信