{"id":"https://openalex.org/W7117482891","doi":"https://doi.org/10.1109/dicta68720.2025.11302474","title":"Predictive Imbalance: Bipartite Matching in DETR-Like Detectors","display_name":"Predictive Imbalance: Bipartite Matching in DETR-Like Detectors","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7117482891","doi":"https://doi.org/10.1109/dicta68720.2025.11302474"},"language":null,"primary_location":{"id":"doi:10.1109/dicta68720.2025.11302474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta68720.2025.11302474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","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/A5121474057","display_name":"Mohammad Mahbub Alam","orcid":null},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]},{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Mohammad Mahbub Alam","raw_affiliation_strings":["School of Systems & Computing, University of New South Wales,Canberra,Australia"],"affiliations":[{"raw_affiliation_string":"School of Systems & Computing, University of New South Wales,Canberra,Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5121474057"],"corresponding_institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66112147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9713000059127808,"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":0.9713000059127808,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.01269999984651804,"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":0.0026000000070780516,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6646999716758728},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.6633999943733215},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6557999849319458},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5397999882698059},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5178999900817871},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.4984999895095825},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.4887000024318695},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46219998598098755}],"concepts":[{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6646999716758728},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6633999943733215},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6557999849319458},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5397999882698059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5181000232696533},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5178999900817871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5163000226020813},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.4984999895095825},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.4887000024318695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4575999975204468},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4074000120162964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3921999931335449},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3725999891757965},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36039999127388},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dicta68720.2025.11302474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta68720.2025.11302474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W607748843","https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2183182206","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2601564443","https://openalex.org/W2612624696","https://openalex.org/W2962766617","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2966926453","https://openalex.org/W2989604896","https://openalex.org/W2990763144","https://openalex.org/W3012573144","https://openalex.org/W3034756453","https://openalex.org/W3035473155","https://openalex.org/W3096609285","https://openalex.org/W3196024568","https://openalex.org/W3213476061","https://openalex.org/W4214489586","https://openalex.org/W4214507171","https://openalex.org/W4296743665","https://openalex.org/W4312312588","https://openalex.org/W4313119505","https://openalex.org/W4386076325","https://openalex.org/W4390871672"],"related_works":[],"abstract_inverted_index":{"In":[0],"Transformer-based":[1],"object":[2],"detection":[3,119,129],"architectures,":[4],"such":[5],"as":[6],"DETR,":[7],"bipartite":[8],"matching":[9,24,81],"critically":[10],"associates":[11],"predicted":[12],"bounding":[13,91],"boxes":[14],"with":[15,39,73,131],"ground-truth":[16],"labels.":[17],"However,":[18],"the":[19,61,80,127,153],"Hungarian":[20],"algorithm":[21],"used":[22],"for":[23],"often":[25],"encounters":[26],"predictive":[27,150],"imbalance,":[28,151],"a":[29,65,86,132],"mismatch":[30],"between":[31],"classification":[32,41,71],"confidence":[33],"and":[34,48,55,116],"localization":[35,46,74,97],"accuracy.":[36,120],"Specifically,":[37],"predictions":[38],"high":[40],"scores":[42,72],"may":[43],"have":[44],"poor":[45],"accuracy":[47],"vice":[49],"versa,":[50],"leading":[51],"to":[52,69],"training":[53,112],"instability":[54],"suboptimal":[56],"performance.":[57],"This":[58],"study":[59],"addresses":[60],"issue":[62],"by":[63],"introducing":[64],"location-aware":[66],"distillation(LAD)":[67],"loss":[68],"align":[70],"accuracy,":[75],"thus":[76],"promoting":[77],"consistency":[78],"within":[79],"process.":[82],"Additionally,":[83],"we":[84],"propose":[85],"simplified":[87],"triangle":[88],"loss\u2013a":[89],"distance-based":[90],"box":[92],"regression":[93],"loss\u2014to":[94],"further":[95],"enhance":[96],"precision.":[98],"Experiments":[99],"conducted":[100],"on":[101,126],"DETR":[102],"variants,":[103],"including":[104],"DINO,":[105],"demonstrate":[106],"that":[107],"our":[108],"approach":[109],"effectively":[110],"stabilizes":[111],"dynamics,":[113],"accelerates":[114],"convergence,":[115],"significantly":[117],"improves":[118],"Our":[121],"method":[122],"achieves":[123],"51.5":[124],"AP":[125],"COCO":[128],"benchmark":[130],"ResNet-50":[133],"backbone,":[134],"surpassing":[135],"baseline":[136],"models":[137],"without":[138],"incurring":[139],"additional":[140],"computational":[141],"overhead.":[142],"These":[143],"findings":[144],"provide":[145],"valuable":[146],"insights":[147],"into":[148],"mitigating":[149],"enhancing":[152],"reliability":[154],"of":[155],"DETR-like":[156],"detectors.":[157]},"counts_by_year":[],"updated_date":"2025-12-30T23:08:21.542490","created_date":"2025-12-29T00:00:00"}