Seyran Khademi, Xiangwei Shi, Tino Mager, R. Siebes, C. Hein, V. D. Boer, J. V. Gemert
{"title":"深度神经网络眼中的观光","authors":"Seyran Khademi, Xiangwei Shi, Tino Mager, R. Siebes, C. Hein, V. D. Boer, J. V. Gemert","doi":"10.1109/eScience.2018.00125","DOIUrl":null,"url":null,"abstract":"We address the interpretability of convolutional neural networks (CNNs) for predicting a geo-location from an image. In a pilot experiment we classify images of Pittsburgh vs Tokyo and visualize the learned CNN filters. We found that varying the CNN architecture leads to variating in the visualized filters. This calls for further investigation of the effective parameters on the interpretability of CNNs.","PeriodicalId":6476,"journal":{"name":"2018 IEEE 14th International Conference on e-Science (e-Science)","volume":"107 1","pages":"407-408"},"PeriodicalIF":0.0000,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Sight-Seeing in the Eyes of Deep Neural Networks\",\"authors\":\"Seyran Khademi, Xiangwei Shi, Tino Mager, R. Siebes, C. Hein, V. D. Boer, J. V. Gemert\",\"doi\":\"10.1109/eScience.2018.00125\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We address the interpretability of convolutional neural networks (CNNs) for predicting a geo-location from an image. In a pilot experiment we classify images of Pittsburgh vs Tokyo and visualize the learned CNN filters. We found that varying the CNN architecture leads to variating in the visualized filters. This calls for further investigation of the effective parameters on the interpretability of CNNs.\",\"PeriodicalId\":6476,\"journal\":{\"name\":\"2018 IEEE 14th International Conference on e-Science (e-Science)\",\"volume\":\"107 1\",\"pages\":\"407-408\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 IEEE 14th International Conference on e-Science (e-Science)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/eScience.2018.00125\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE 14th International Conference on e-Science (e-Science)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/eScience.2018.00125","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
We address the interpretability of convolutional neural networks (CNNs) for predicting a geo-location from an image. In a pilot experiment we classify images of Pittsburgh vs Tokyo and visualize the learned CNN filters. We found that varying the CNN architecture leads to variating in the visualized filters. This calls for further investigation of the effective parameters on the interpretability of CNNs.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
