{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T07:54:22Z","timestamp":1726041262483},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"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":[[2021,10]]},"DOI":"10.1109\/iccv48922.2021.00094","type":"proceedings-article","created":{"date-parts":[[2022,2,28]],"date-time":"2022-02-28T22:08:02Z","timestamp":1646086082000},"page":"885-894","source":"Crossref","is-referenced-by-count":3,"title":["Generating Attribution Maps with Disentangled Masked Backpropagation"],"prefix":"10.1109","author":[{"given":"Adria","family":"Ruiz","sequence":"first","affiliation":[{"name":"CSIC-UPC,Institut de Robotica i Informàtica Industrial,Barcelona,Spain"}]},{"given":"Antonio","family":"Agudo","sequence":"additional","affiliation":[{"name":"CSIC-UPC,Institut de Robotica i Informàtica Industrial,Barcelona,Spain"}]},{"given":"Francesc","family":"Moreno-Noguer","sequence":"additional","affiliation":[{"name":"CSIC-UPC,Institut de Robotica i Informàtica Industrial,Barcelona,Spain"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700808"},{"journal-title":"Eur Conf Comput Vis","article-title":"Top-down Neural Attention by Excitation Backprop","year":"2016","author":"zhang","key":"ref38"},{"journal-title":"Int Conf Machine Learning","article-title":"Axiomatic Attribution for Deep Networks","year":"2017","author":"sundararajan","key":"ref33"},{"journal-title":"Adv Neural Inform Process Syst","article-title":"Full-Gradient Representation for Neural Network Visualization","year":"2019","author":"srinivas","key":"ref32"},{"journal-title":"ICLR Workshop","article-title":"Striving For Simplicity: The All Convolutional Net","year":"2015","author":"springenberg","key":"ref31"},{"journal-title":"Int Conf Machine Learning","article-title":"SmoothGrad: removing noise by adding noise","year":"2017","author":"smilkov","key":"ref30"},{"journal-title":"Eur Conf Comput Vis","article-title":"Visualizing and Understanding Convolutional Networks","year":"2014","author":"zeiler","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_40"},{"journal-title":"Int Conf Machine Learning","article-title":"On the Number of Linear Regions of Convolutional Neural Networks","year":"2020","author":"xiong","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00020"},{"article-title":"A review on deep learning techniques applied to semantic segmentation","year":"2017","author":"garcia-garcia","key":"ref10"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"},{"journal-title":"Int Conf Learn Represent","article-title":"Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness","year":"2019","author":"geirhos","key":"ref11"},{"journal-title":"IEEE Conf Comput Vis Pattern Recog","article-title":"Attribution in Scale and Space","year":"2020","author":"google","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"article-title":"Batch normalization: Accelerating deep network training by reducing internal co-variate shift","year":"2015","author":"ioffe","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00505"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.320"},{"journal-title":"Int Conf Learn Represent","article-title":"Learning how to explain neural networks: Patternnet and patternattribution","year":"2018","author":"kindermans","key":"ref18"},{"journal-title":"Adv Neural Inform Process Syst","article-title":"A unified approach to interpreting model predictions","year":"2017","author":"lundberg","key":"ref19"},{"journal-title":"Int Conf Learn Represent","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","year":"2014","author":"simonyan","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_2"},{"journal-title":"International Conference on Machine Learning ICML 2017","article-title":"Learning Important Features Through Propagating Activation Differences","year":"2017","author":"shrikumar","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1098\/rsif.2017.0387"},{"journal-title":"Int Conf Learn Represent","article-title":"Very deep convolutional networks for large-scale image recognition","year":"2015","author":"simonyan","key":"ref29"},{"journal-title":"IEEE Conf Comput Vis Pattern Recog","article-title":"Sam: The sensitivity of attribution methods to hyperparameters","year":"2020","author":"bansal","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00304"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"journal-title":"Int Conf Learn Represent","article-title":"Towards better understanding of gradient-based attribution methods for deep neural networks","year":"2018","author":"ancona","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"journal-title":"Adv Neural Inform Process Syst","article-title":"Sanity checks for saliency maps","year":"2018","author":"adebayo","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.11.008"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00886"},{"journal-title":"Brit Mach Vis Conf","article-title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","year":"2018","author":"petsiuk","key":"ref21"},{"journal-title":"Int Conf Learn Represent","article-title":"Visualizing Deep Neural Network Decisions: Prediction Difference Analysis","year":"2017","author":"zintgraf","key":"ref42"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"journal-title":"International conference on Knowledge discovery and data mining","article-title":"Model-agnostic interpretability of machine learning","year":"2016","author":"ribeiro","key":"ref23"},{"journal-title":"Int Conf Machine Learning","article-title":"Learning important features through propagating activation differences","year":"2017","author":"shrikumar","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"}],"event":{"name":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","start":{"date-parts":[[2021,10,10]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2021,10,17]]}},"container-title":["2021 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9709627\/9709628\/09710348.pdf?arnumber=9710348","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T20:18:42Z","timestamp":1658780322000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9710348\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iccv48922.2021.00094","relation":{},"subject":[],"published":{"date-parts":[[2021,10]]}}}
