{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T19:50:30Z","timestamp":1767383430150,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T00:00:00Z","timestamp":1665878400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,16]]},"DOI":"10.1109\/icip46576.2022.9897282","type":"proceedings-article","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T17:27:24Z","timestamp":1667496444000},"page":"516-520","source":"Crossref","is-referenced-by-count":4,"title":["Measurably Stronger Explanation Reliability Via Model Canonization"],"prefix":"10.1109","author":[{"given":"Franz","family":"Motzkus","sequence":"first","affiliation":[{"name":"Fraunhofer Heinrich Hertz Institute,Department of Artificial Intelligence,Berlin,Germany,10587"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leander","family":"Weber","sequence":"additional","affiliation":[{"name":"Fraunhofer Heinrich Hertz Institute,Department of Artificial Intelligence,Berlin,Germany,10587"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastian","family":"Lapuschkin","sequence":"additional","affiliation":[{"name":"Fraunhofer Heinrich Hertz Institute,Department of Artificial Intelligence,Berlin,Germany,10587"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3060483"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref3","first-page":"3145","article-title":"Learning important features through propagating activation differences","volume-title":"Proc. ICML","volume":"70 of Proc. MLR","author":"Shrikumar"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1995.488997"},{"key":"ref5","first-page":"1803","article-title":"How to explain individual classification decisions","volume":"11","author":"Baehrens","year":"2010","journal-title":"JMLR"},{"key":"ref6","first-page":"1135","article-title":"\"Why should i trust you?","volume-title":"explaining the predictions of any classifier,\" in Proc. ACM SIGKDD","author":"Ribeiro"},{"article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","volume-title":"Proc. ICLR","author":"Simonyan","key":"ref7"},{"key":"ref8","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"Proc. ICML","author":"Sundararajan"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6_13"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206975"},{"key":"ref11","first-page":"448","article-title":"Batchnormalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. ICML","volume":"37 of JMLR Workshop Conf. Proc","author":"Ioffe"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20518-8_24"},{"article-title":"Breaking batch normalization for better explainability of deep neural networks through layer-wise relevance propagation","year":"2020","author":"Guillemot","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107899"},{"article-title":"Software for dataset-wide XAI: from local explanations to global insights with zennit, corelay, and virelay","year":"2021","author":"Anders","key":"ref16"},{"article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. ICLR","author":"Simonyan","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2599820"},{"article-title":"Notes on canonization for resnets and densenets","year":"2020","author":"Binder","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1059-x"},{"article-title":"Striving for simplicity: The all convolutional net","volume-title":"Proc. ICLR","author":"Springenberg","key":"ref22"},{"article-title":"Not just a black box: Learning important features through propagating activation differences","year":"2016","author":"Shrikumar","key":"ref23"}],"event":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2022,10,16]]},"location":"Bordeaux, France","end":{"date-parts":[[2022,10,19]]}},"container-title":["2022 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9897158\/9897159\/09897282.pdf?arnumber=9897282","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T15:55:05Z","timestamp":1705938905000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9897282\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,16]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icip46576.2022.9897282","relation":{},"subject":[],"published":{"date-parts":[[2022,10,16]]}}}