{"id":"https://openalex.org/W7129626135","doi":"https://doi.org/10.1109/icipw68931.2025.11386287","title":"Tri-Axial Scaling in Aerial Object Detection: Model Size, Dataset Size and Quality, and Test-Time Inference in the Cadot Challenge","display_name":"Tri-Axial Scaling in Aerial Object Detection: Model Size, Dataset Size and Quality, and Test-Time Inference in the Cadot Challenge","publication_year":2025,"publication_date":"2025-09-14","ids":{"openalex":"https://openalex.org/W7129626135","doi":"https://doi.org/10.1109/icipw68931.2025.11386287"},"language":null,"primary_location":{"id":"doi:10.1109/icipw68931.2025.11386287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icipw68931.2025.11386287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing Workshops (ICIPW)","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/A5081035449","display_name":"Yi Jie Wong","orcid":"https://orcid.org/0000-0003-4598-2653"},"institutions":[{"id":"https://openalex.org/I931681460","display_name":"Universiti Tunku Abdul Rahman","ror":"https://ror.org/050pq4m56","country_code":"MY","type":"education","lineage":["https://openalex.org/I931681460"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Yi Jie Wong","raw_affiliation_strings":["Universiti Tunku Abdul Rahman,Malaysia"],"affiliations":[{"raw_affiliation_string":"Universiti Tunku Abdul Rahman,Malaysia","institution_ids":["https://openalex.org/I931681460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114163349","display_name":"Jing Tan","orcid":"https://orcid.org/0009-0003-7249-0483"},"institutions":[{"id":"https://openalex.org/I931681460","display_name":"Universiti Tunku Abdul Rahman","ror":"https://ror.org/050pq4m56","country_code":"MY","type":"education","lineage":["https://openalex.org/I931681460"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Jing Jie Tan","raw_affiliation_strings":["Universiti Tunku Abdul Rahman,Malaysia"],"affiliations":[{"raw_affiliation_string":"Universiti Tunku Abdul Rahman,Malaysia","institution_ids":["https://openalex.org/I931681460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126216737","display_name":"Mau-Luen Tham","orcid":null},"institutions":[{"id":"https://openalex.org/I931681460","display_name":"Universiti Tunku Abdul Rahman","ror":"https://ror.org/050pq4m56","country_code":"MY","type":"education","lineage":["https://openalex.org/I931681460"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Mau-Luen Tham","raw_affiliation_strings":["Universiti Tunku Abdul Rahman,Malaysia"],"affiliations":[{"raw_affiliation_string":"Universiti Tunku Abdul Rahman,Malaysia","institution_ids":["https://openalex.org/I931681460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005737764","display_name":"Ban-Hoe Kwan","orcid":"https://orcid.org/0000-0001-7094-8612"},"institutions":[{"id":"https://openalex.org/I931681460","display_name":"Universiti Tunku Abdul Rahman","ror":"https://ror.org/050pq4m56","country_code":"MY","type":"education","lineage":["https://openalex.org/I931681460"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Ban-Hoe Kwan","raw_affiliation_strings":["Universiti Tunku Abdul Rahman,Malaysia"],"affiliations":[{"raw_affiliation_string":"Universiti Tunku Abdul Rahman,Malaysia","institution_ids":["https://openalex.org/I931681460"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040863689","display_name":"Yan Chai Hum","orcid":"https://orcid.org/0000-0002-9657-8311"},"institutions":[{"id":"https://openalex.org/I931681460","display_name":"Universiti Tunku Abdul Rahman","ror":"https://ror.org/050pq4m56","country_code":"MY","type":"education","lineage":["https://openalex.org/I931681460"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Yan Chai Hum","raw_affiliation_strings":["Universiti Tunku Abdul Rahman,Malaysia"],"affiliations":[{"raw_affiliation_string":"Universiti Tunku Abdul Rahman,Malaysia","institution_ids":["https://openalex.org/I931681460"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081035449"],"corresponding_institution_ids":["https://openalex.org/I931681460"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74338537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9617999792098999,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9617999792098999,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.006300000008195639,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.004600000102072954,"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/robustness","display_name":"Robustness (evolution)","score":0.7400000095367432},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7337999939918518},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6150000095367432},{"id":"https://openalex.org/keywords/aerial-imagery","display_name":"Aerial imagery","score":0.51910001039505},{"id":"https://openalex.org/keywords/aerial-image","display_name":"Aerial image","score":0.49959999322891235},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4722000062465668},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4587000012397766},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4456000030040741},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4244999885559082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623999714851379},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7400000095367432},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7337999939918518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6554999947547913},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6150000095367432},{"id":"https://openalex.org/C2987819851","wikidata":"https://www.wikidata.org/wiki/Q191839","display_name":"Aerial imagery","level":2,"score":0.51910001039505},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.49959999322891235},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4722000062465668},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45879998803138733},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44600000977516174},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.364300012588501},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3215000033378601},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29739999771118164},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C3019973339","wikidata":"https://www.wikidata.org/wiki/Q899523","display_name":"Object based","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icipw68931.2025.11386287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icipw68931.2025.11386287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Image Processing Workshops (ICIPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.7729039788246155,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2962749812","https://openalex.org/W3034971973","https://openalex.org/W3096609285","https://openalex.org/W3122028341","https://openalex.org/W3127743092","https://openalex.org/W3162833667","https://openalex.org/W3180134609","https://openalex.org/W3184246247","https://openalex.org/W4310553620","https://openalex.org/W4376607793","https://openalex.org/W4386525519","https://openalex.org/W4401894250","https://openalex.org/W4402865423","https://openalex.org/W4402916053","https://openalex.org/W4403511756","https://openalex.org/W4406460615","https://openalex.org/W4409709894","https://openalex.org/W4416251556"],"related_works":[],"abstract_inverted_index":{"Advancements":[0],"in":[1,18,24,125],"remote":[2],"sensing":[3],"technology":[4],"and":[5,34,37,68,70,92,101,110,136],"deep":[6],"learning":[7],"techniques":[8],"have":[9],"paved":[10],"the":[11,76,123,126],"way":[12],"for":[13,53],"accurate":[14],"aerial":[15,54],"object":[16,22,55],"detection":[17,23,56],"urban":[19],"environments.":[20],"However,":[21],"these":[25,45],"settings":[26],"remains":[27],"challenging":[28],"due":[29],"to":[30,82,96,113],"dense":[31],"scenes,":[32],"small":[33],"occluded":[35],"objects,":[36],"high":[38],"variability":[39],"across":[40],"geographic":[41],"domains.":[42],"To":[43],"tackle":[44],"challenges,":[46],"we":[47,74,87,106],"propose":[48],"a":[49],"tri-axial":[50],"scaling":[51],"framework":[52],"that":[57],"systematically":[58],"improves":[59],"performance":[60],"along":[61],"three":[62],"dimensions:":[63],"model":[64],"size,":[65],"dataset":[66],"size":[67],"quality,":[69],"inference":[71],"strategy.":[72],"First,":[73],"explore":[75],"use":[77],"of":[78],"larger":[79],"backbone":[80],"architectures":[81],"enhance":[83],"feature":[84],"representation.":[85],"Second,":[86],"apply":[88],"diffusion-based":[89],"data":[90,99],"augmentation":[91,109],"balanced":[93],"class":[94,103],"sampling":[95],"improve":[97],"training":[98],"diversity":[100],"address":[102],"imbalance.":[104],"Third,":[105],"incorporate":[107],"test-time":[108],"ensemble":[111],"models":[112,138],"increase":[114],"robustness":[115],"during":[116],"inference.":[117],"Our":[118],"solution":[119],"ranks":[120],"first":[121],"on":[122],"leaderboard":[124],"IEEE":[127],"ICIP":[128],"2025":[129],"-":[130],"CADOT":[131],"challenge.":[132],"The":[133],"source":[134],"code":[135],"pretrained":[137],"are":[139],"available":[140],"at":[141],"https://github.com/yjwong1999/Double_J_CADOT_Challenge.":[142]},"counts_by_year":[],"updated_date":"2026-02-19T06:27:42.648592","created_date":"2026-02-18T00:00:00"}