{"id":"https://openalex.org/W7133338704","doi":"https://doi.org/10.48550/arxiv.2603.01161","title":"GRAD-Former: Gated Robust Attention-based Differential Transformer for Change Detection","display_name":"GRAD-Former: Gated Robust Attention-based Differential Transformer for Change Detection","publication_year":2026,"publication_date":"2026-03-01","ids":{"openalex":"https://openalex.org/W7133338704","doi":"https://doi.org/10.48550/arxiv.2603.01161"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.01161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01161","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.01161","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127935426","display_name":"Durgesh Ameta","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ameta, Durgesh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128010060","display_name":"Ujjwal Mishra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mishra, Ujjwal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091700001","display_name":"Praful Hambarde","orcid":"https://orcid.org/0000-0002-7976-9095"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hambarde, Praful","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5028888771","display_name":"Amit K. Shukla","orcid":"https://orcid.org/0000-0002-7581-782X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shukla, Amit","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5127935426"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10689","display_name":"Remote-Sensing Image Classification","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10111","display_name":"Remote Sensing in Agriculture","score":0.0024999999441206455,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11659","display_name":"Advanced Image Fusion Techniques","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.5881999731063843},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.5507000088691711},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5273000001907349},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4832000136375427},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4765999913215637},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.436599999666214},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.42980000376701355},{"id":"https://openalex.org/keywords/earth-observation","display_name":"Earth observation","score":0.38659998774528503},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3693999946117401}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7734000086784363},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.5881999731063843},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5273000001907349},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4832000136375427},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4765999913215637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4756999909877777},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3894999921321869},{"id":"https://openalex.org/C39399123","wikidata":"https://www.wikidata.org/wiki/Q1348989","display_name":"Earth observation","level":3,"score":0.38659998774528503},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3693999946117401},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3571999967098236},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3481000065803528},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.258899986743927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.01161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01161","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.01161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01161","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.7861908674240112,"id":"https://metadata.un.org/sdg/14","display_name":"Life below water"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Change":[0],"detection":[1,217],"(CD)":[2],"in":[3,83],"remote":[4,214],"sensing":[5,215],"aims":[6],"to":[7,43,60,75,160,185],"identify":[8],"semantic":[9],"differences":[10],"between":[11],"satellite":[12,64],"images":[13,65],"captured":[14,167],"at":[15],"different":[16],"times.":[17],"While":[18],"deep":[19],"learning":[20],"has":[21],"significantly":[22],"advanced":[23],"this":[24],"field,":[25],"existing":[26,186],"approaches":[27],"based":[28],"on":[29],"convolutional":[30],"neural":[31],"networks":[32],"(CNNs),":[33],"transformers":[34],"and":[35,66,115,120,138,146,151,199],"Selective":[36,133],"State":[37],"Space":[38],"Models":[39],"(SSMs)":[40],"still":[41],"struggle":[42],"precisely":[44],"delineate":[45],"change":[46,216],"regions.":[47],"In":[48],"particular,":[49],"traditional":[50],"transformer-based":[51],"methods":[52],"suffer":[53],"from":[54],"quadratic":[55],"computational":[56],"complexity":[57],"when":[58],"applied":[59],"very":[61],"high-resolution":[62],"(VHR)":[63],"often":[67],"perform":[68],"poorly":[69],"with":[70,111],"limited":[71],"training":[72],"data,":[73],"leading":[74],"under-utilization":[76],"of":[77,107],"the":[78,132,139,166,191,197,201],"rich":[79],"spatial":[80],"information":[81],"available":[82],"VHR":[84],"imagery.":[85],"We":[86],"present":[87],"GRAD-Former,":[88],"a":[89,108,210],"novel":[90,109],"framework":[91,105,208],"that":[92],"enhances":[93],"contextual":[94,126],"understanding":[95],"while":[96,164,203],"maintaining":[97],"efficiency":[98],"through":[99,128],"reduced":[100],"model":[101],"size.":[102],"The":[103],"proposed":[104,130],"consists":[106],"encoder":[110],"Adaptive":[112],"Feature":[113,141],"Relevance":[114],"Refinement":[116,142],"(AFRAR)":[117],"module,":[118],"fusion":[119],"decoder":[121],"blocks.":[122],"AFRAR":[123],"integrates":[124],"global-local":[125],"awareness":[127],"two":[129],"components:":[131],"Embedding":[134],"Amplification":[135],"(SEA)":[136],"module":[137],"Global-Local":[140],"(GLFR)":[143],"module.":[144],"SEA":[145],"GLFR":[147],"leverage":[148],"gating":[149],"mechanisms":[150],"differential":[152],"attention,":[153],"respectively,":[154],"which":[155],"generates":[156],"multiple":[157],"softmax":[158],"heaps":[159],"capture":[161],"important":[162],"features":[163],"minimizing":[165],"irreverent":[168],"features.":[169],"Multiple":[170],"experiments":[171],"across":[172,195],"three":[173],"challenging":[174],"CD":[175],"datasets":[176,202],"(LEVIR-CD,":[177],"CDD,":[178],"DSIFN-CD)":[179],"demonstrate":[180],"GRAD-Former's":[181],"superior":[182],"performance":[183],"compared":[184],"approaches.":[187],"Notably,":[188],"GRAD-Former":[189],"outperforms":[190],"current":[192],"state-of-the-art":[193],"models":[194],"all":[196,200],"metrics":[198],"using":[204],"fewer":[205],"parameters.":[206],"Our":[207,219],"establishes":[209],"new":[211],"benchmark":[212],"for":[213],"performance.":[218],"code":[220],"will":[221],"be":[222],"released":[223],"at:":[224],"https://github.com/Ujjwal238/GRAD-Former":[225]},"counts_by_year":[],"updated_date":"2026-03-04T07:09:34.246503","created_date":"2026-03-04T00:00:00"}