{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T20:53:19Z","timestamp":1775508799957,"version":"3.50.1"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP 180100958"],"award-info":[{"award-number":["DP 180100958"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Industrial Transformation Research Hub","award":["IH180100002"],"award-info":[{"award-number":["IH180100002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpami.2026.3651260","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:00:30Z","timestamp":1768255230000},"page":"5536-5551","source":"Crossref","is-referenced-by-count":0,"title":["Neuron Abandoning Attention Flow: Visual Explanation of Dynamics Inside CNN Models"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4594-1416","authenticated-orcid":false,"given":"Yi","family":"Liao","sequence":"first","affiliation":[{"name":"School of Engineering and Built Environment, Griffith University, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5382-5351","authenticated-orcid":false,"given":"Yongsheng","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Engineering and Built Environment, Griffith University, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4904-1826","authenticated-orcid":false,"given":"Weichuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref3","first-page":"3637","article-title":"Matching networks for one shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Vinyals","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06074-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992207"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.06.030"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3066410"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3670685"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-022-00867-8"},{"key":"ref11","first-page":"3145","article-title":"Learning important features through propagating activation differences","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Shrikumar","year":"2017"},{"key":"ref12","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sundararajan","year":"2017"},{"key":"ref13","first-page":"1","article-title":"RISE: Randomized input sampling for explanation of black-box models","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Petsiuk","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01096"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089943"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01470"},{"key":"ref20","first-page":"26871","article-title":"PolarStream: Streaming object detection and segmentation with polar pillars","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.354"},{"key":"ref22","first-page":"2668","article-title":"Interpretability beyond feature attribution: Quantitative testing with concept activation vectors","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2018"},{"key":"ref23","first-page":"4124","article-title":"Full-gradient representation for neural network visualization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Srinivas","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.338"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1059-x"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5244\/C.34.146"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718874"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1214\/09-IMSCOLL514"},{"key":"ref32","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statis.","volume":"15","author":"Glorot","year":"2011"},{"issue":"1","key":"ref33","first-page":"1","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"Proc. ICML Workshop Deep Learn. Audio, Speech Lang. Process.","volume":"30","author":"Maas","year":"2013"},{"key":"ref34","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky","year":"2012"},{"key":"ref35","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref37","first-page":"1","article-title":"BAM: Bottleneck attention module","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Park","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00516"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref42","article-title":"The Caltech-UCSD birds 200-2011 Dataset","author":"Wah","year":"2011"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00893"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/s20061594"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref46","first-page":"10285","article-title":"A theoretical analysis of the learning dynamics under class imbalance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Francazi","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"ref48","first-page":"38516","article-title":"On feature learning in the presence of spurious correlations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Izmailov","year":"2022"},{"key":"ref49","article-title":"Spurious correlations in machine learning: A survey","author":"Ye","year":"2024"},{"key":"ref50","first-page":"8346","article-title":"An investigation of why overparameterization exacerbates spurious correlations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sagawa","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00198"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11474534\/11342296.pdf?arnumber=11342296","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:56:28Z","timestamp":1775505388000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342296\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":54,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3651260","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}