{"id":"https://openalex.org/W4392904024","doi":"https://doi.org/10.1109/icassp48485.2024.10446537","title":"Blenda: Domain Adaptive Object Detection Through Diffusion-Based Blending","display_name":"Blenda: Domain Adaptive Object Detection Through Diffusion-Based Blending","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904024","doi":"https://doi.org/10.1109/icassp48485.2024.10446537"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112985472","display_name":"Tzuhsuan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tzuhsuan Huang","raw_affiliation_strings":["Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013198571","display_name":"Chen-Che Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chen-Che Huang","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109675882","display_name":"Chung-Hao Ku","orcid":null},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Hao Ku","raw_affiliation_strings":["Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010007692","display_name":"Jun-Cheng Chen","orcid":"https://orcid.org/0000-0002-0209-8932"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jun-Cheng Chen","raw_affiliation_strings":["Academia Sinica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4437,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89925734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4075","last_page":"4079"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.814448356628418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6445485353469849},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6185306906700134},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.588737428188324},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5493752360343933},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5374897122383118},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5207290649414062},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4937022626399994},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.47873303294181824},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4457990825176239},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4245927929878235},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4187087416648865},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4104546308517456},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.1018957793712616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1002638041973114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.814448356628418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6445485353469849},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6185306906700134},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.588737428188324},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5493752360343933},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5374897122383118},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5207290649414062},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4937022626399994},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.47873303294181824},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4457990825176239},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4245927929878235},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4187087416648865},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4104546308517456},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.1018957793712616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1002638041973114},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1686810756","https://openalex.org/W1882958252","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2748021867","https://openalex.org/W2765407302","https://openalex.org/W2908510526","https://openalex.org/W2953070460","https://openalex.org/W2962793481","https://openalex.org/W2982770724","https://openalex.org/W3034937575","https://openalex.org/W3035564946","https://openalex.org/W3096609285","https://openalex.org/W3121281282","https://openalex.org/W3122239467","https://openalex.org/W3166409449","https://openalex.org/W3186269967","https://openalex.org/W3206713300","https://openalex.org/W4282945772","https://openalex.org/W4283807782","https://openalex.org/W4285600811","https://openalex.org/W4312681219","https://openalex.org/W4312775058","https://openalex.org/W4312993742","https://openalex.org/W4313160574","https://openalex.org/W4319300551","https://openalex.org/W4386071781","https://openalex.org/W4386072135","https://openalex.org/W4386076215","https://openalex.org/W6620707391","https://openalex.org/W6637373629","https://openalex.org/W6639480849","https://openalex.org/W6733814495","https://openalex.org/W6745136726","https://openalex.org/W6757817989","https://openalex.org/W6784094891","https://openalex.org/W6838694358"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2501551404","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W4385583601","https://openalex.org/W4395685956","https://openalex.org/W4254199101","https://openalex.org/W4299904075","https://openalex.org/W2565214228"],"abstract_inverted_index":{"Unsupervised":[0],"domain":[1,16,28,44,62,98,127,175],"adaptation":[2,65,114],"(UDA)":[3],"aims":[4],"to":[5,17,139,171],"transfer":[6],"a":[7,39],"model":[8,89],"learned":[9],"using":[10,83],"labeled":[11],"data":[12,19],"from":[13,112],"the":[14,21,26,32,51,55,75,92,96,122,125,137,150,155],"source":[15,33,76],"unlabeled":[18],"in":[20,136],"target":[22,35,97],"domain.":[23],"To":[24],"address":[25],"large":[27],"gap":[29],"issue":[30],"between":[31],"and":[34,58,101],"domains,":[36],"we":[37,143],"propose":[38],"novel":[40],"regularization":[41],"method":[42,167],"for":[43,64],"adaptive":[45,128,176],"object":[46,129,177],"detection,":[47],"BlenDA,":[48],"by":[49,72,158],"generating":[50],"pseudo":[52],"samples":[53,69],"of":[54,95,124,174],"intermediate":[56,68],"domains":[57],"their":[59,79],"corresponding":[60,80],"soft":[61],"labels":[63],"training.":[66],"The":[67,179],"are":[70],"generated":[71],"dynamically":[73],"blending":[74],"images":[77,82],"with":[78],"translated":[81],"an":[84,145],"off-the-shelf":[85],"pre-trained":[86],"text-to-image":[87],"diffusion":[88],"which":[90],"takes":[91],"text":[93],"label":[94],"as":[99],"input":[100],"has":[102],"demonstrated":[103],"superior":[104],"image-to-image":[105],"translation":[106],"quality.":[107],"Based":[108],"on":[109,149],"experimental":[110],"results":[111],"two":[113],"benchmarks,":[115],"our":[116,165],"proposed":[117,166],"approach":[118],"can":[119],"significantly":[120],"enhance":[121],"performance":[123],"state-of-the-art":[126,157],"detector,":[130],"Adversarial":[131],"Query":[132],"Transformer":[133],"(AQT).":[134],"Particularly,":[135],"Cityscapes":[138,141,152],"Foggy":[140,151],"adaptation,":[142],"achieve":[144],"impressive":[146],"53.4%":[147],"mAP":[148],"dataset,":[153],"surpassing":[154],"previous":[156],"1.5%.":[159],"It":[160],"is":[161,168,181],"worth":[162],"noting":[163],"that":[164],"also":[169],"applicable":[170],"various":[172],"paradigms":[173],"detection.":[178],"code":[180],"available":[182],"at":[183],"https://github.com/aiiu-lab/BlenDA":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}