{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T23:11:39Z","timestamp":1775862699075,"version":"3.50.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Defense Challengeable Future Technology Program of the Agency for Defense Development, South Korea"},{"DOI":"10.13039\/501100003696","name":"Electronics and Telecommunications Research Institute (ETRI) grant","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003696","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003696","name":"Korean Government","doi-asserted-by":"publisher","award":["20ZS1100"],"award-info":[{"award-number":["20ZS1100"]}],"id":[{"id":"10.13039\/501100003696","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3074640","type":"journal-article","created":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T01:49:45Z","timestamp":1619056185000},"page":"62332-62346","source":"Crossref","is-referenced-by-count":5,"title":["An Alternating Training Method of Attention-Based Adapters for Visual Explanation of Multi-Domain Satellite Images"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9743-378X","authenticated-orcid":false,"given":"Heejae","family":"Kim","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4753-4021","authenticated-orcid":false,"given":"Kyungchae","family":"Lee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3687-2989","authenticated-orcid":false,"given":"Changha","family":"Lee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9987-8088","authenticated-orcid":false,"given":"Sanghyun","family":"Hwang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3970-7308","authenticated-orcid":false,"given":"Chan-Hyun","family":"Youn","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref38","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016","journal-title":"arXiv 1607 08022"},{"key":"ref33","first-page":"3319","article-title":"Axiomatic attribution for deep networks","author":"sundararajan","year":"2017","journal-title":"Proc ICML"},{"key":"ref32","first-page":"4768","article-title":"A unified approach to interpreting model predictions","author":"lundberg","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref37","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2872879"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00736"},{"key":"ref34","first-page":"1","article-title":"Domain separation networks","author":"bousmalis","year":"2016","journal-title":"Proc NeurIPS"},{"key":"ref60","year":"2015","journal-title":"Caffenet"},{"key":"ref61","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Proc AISTATS"},{"key":"ref28","first-page":"1","article-title":"Network in network","author":"lin","year":"2014","journal-title":"Proc ICLR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3008323"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2968771"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5379"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00134"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00104"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3020804"},{"key":"ref24","first-page":"111","article-title":"Domain adaptation for degraded remote scene classification","author":"yang","year":"2020","journal-title":"Proc ICARCV"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2958123"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3006161"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2985072"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref58","first-page":"7184","article-title":"On the linear speedup analysis of communication efficient momentum SGD for distributed non-convex optimization","author":"yu","year":"2019","journal-title":"Proc ICML"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"ref56","first-page":"2530","article-title":"A linear speedup analysis of distributed deep learning with sparse and quantized communication","author":"jiang","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref55","first-page":"1","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","author":"lian","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1137\/120880811"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45631-7_39"},{"key":"ref52","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCES.2018.8639467"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/rs10121890"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00047"},{"key":"ref12","first-page":"1","article-title":"Learning multiple visual domains with residual adapters","author":"rebuffi","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref13","article-title":"Universal representations: The missing link between faces, text, planktons, and cat breeds","author":"bilen","year":"2017","journal-title":"arXiv 1701 07275"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2700322"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2783902"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2864987"},{"key":"ref18","first-page":"12325","article-title":"Satellite image time series classification with pixel-set encoders and temporal self-attention","author":"garnot","year":"2020","journal-title":"Proc CVPR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2018.2795753"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-16185-w"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref5","author":"arora","year":"2018","journal-title":"Getting Started With SpaceNet"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref49","article-title":"DA2: Deep attention adapter for memory-efficient on-device multi-domain learning","author":"yang","year":"2020","journal-title":"arXiv 2012 01362"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.01.004"},{"key":"ref46","article-title":"Not all domains are equally complex: Adaptive multi-domain learning","author":"senhaji","year":"2020","journal-title":"arXiv 2003 11504"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","article-title":"Latent domain learning with dynamic residual adapters","author":"deecke","year":"2020","journal-title":"arXiv 2006 00996"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00332"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00847"},{"key":"ref41","article-title":"Incremental learning through deep adaptation","author":"rosenfeld","year":"2017","journal-title":"arXiv 1705 04228"},{"key":"ref44","article-title":"What and where: Learn to plug adapters via NAS for multi-domain learning","author":"zhao","year":"2020","journal-title":"arXiv 2007 12415"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00557"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09410224.pdf?arnumber=9410224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:44Z","timestamp":1639770944000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9410224\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3074640","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}