{"id":"https://openalex.org/W7204901955","doi":"https://doi.org/10.1109/tip.2026.3727903","title":"From Generation to Optimization: Improving Pseudo Labels for Semi-Supervised Object Detection","display_name":"From Generation to Optimization: Improving Pseudo Labels for Semi-Supervised Object Detection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204901955","doi":"https://doi.org/10.1109/tip.2026.3727903","pmid":"https://pubmed.ncbi.nlm.nih.gov/42678834"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3727903","doi":"https://doi.org/10.1109/tip.2026.3727903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3727903","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-a","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-2","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W7204901955"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"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/A5011324535","display_name":"Xi Yang","orcid":"https://orcid.org/0000-0002-5791-3674","observed_orcids":["https://orcid.org/0000-0002-5791-3674"]},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Yang","raw_affiliation_strings":["Xidian University"],"raw_orcid":"https://orcid.org/0000-0002-5791-3674","affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100781848","display_name":"Penghui Li","orcid":"https://orcid.org/0000-0003-4709-6874","observed_orcids":["https://orcid.org/0000-0003-4709-6874","https://orcid.org/0009-0006-3831-4357"]},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Penghui Li","raw_affiliation_strings":["Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042507268","display_name":"Nannan Wang","orcid":"https://orcid.org/0000-0002-4695-6134","observed_orcids":["https://orcid.org/0000-0002-4695-6134","https://orcid.org/0000-0003-1435-489X"]},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nannan Wang","raw_affiliation_strings":["Xidian University"],"raw_orcid":"https://orcid.org/0000-0002-4695-6134","affiliations":[{"raw_affiliation_string":"Xidian University","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"9414","last_page":"9429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7529000043869019,"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":0.7529000043869019,"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":0.23690000176429749,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.002099999925121665,"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/semi-supervised-object-detection","display_name":"semi-supervised object detection","score":0.9990000128746033},{"id":"https://openalex.org/keywords/pseudo-labeling","display_name":"pseudo-labeling","score":0.8100000023841858},{"id":"https://openalex.org/keywords/pseudo-label-generation","display_name":"pseudo-label generation","score":0.8259999752044678},{"id":"https://openalex.org/keywords/instance-weighting","display_name":"instance weighting","score":0.5329999923706055},{"id":"https://openalex.org/keywords/local-voting","display_name":"local voting","score":0.8159999847412109},{"id":"https://openalex.org/keywords/auxiliary-loss","display_name":"auxiliary loss","score":0.6340000033378601},{"id":"https://openalex.org/keywords/label-quality","display_name":"label quality","score":0.367000013589859}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6996999979019165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.664900004863739},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6632000207901001},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6543999910354614},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4629000127315521},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.44040000438690186},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.4255000054836273},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.41940000653266907},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.362199991941452},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3488999903202057},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3127000033855438},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3089999854564667},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C182521987","wikidata":"https://www.wikidata.org/wiki/Q2493877","display_name":"Viola\u2013Jones object detection framework","level":5,"score":0.3003000020980835},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.29429998993873596},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.2547000050544739},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2515000104904175},{"id":"https://openalex.org/C2988922011","wikidata":"https://www.wikidata.org/wiki/Q5449244","display_name":"Filtering theory","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3727903","doi":"https://doi.org/10.1109/tip.2026.3727903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3727903","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-a","cwts-core","dongbi-a","doyens","jufo-3","ki-jl-2","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:42678834","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42678834","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2588230043","display_name":null,"funder_award_id":"2024GX-ZDCYL-02-10","funder_id":"https://openalex.org/F4320336350","funder_display_name":"Key Research and Development Projects of Shaanxi Province"},{"id":"https://openalex.org/G5453829200","display_name":null,"funder_award_id":"62372348","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8713760102","display_name":null,"funder_award_id":"QTZX26138","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320336350","display_name":"Key Research and Development Projects of Shaanxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1483870316","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2124351162","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2962749812","https://openalex.org/W2963150697","https://openalex.org/W2982770724","https://openalex.org/W3018757597","https://openalex.org/W3111156583","https://openalex.org/W3158661000","https://openalex.org/W3170602832","https://openalex.org/W3172507542","https://openalex.org/W3176748778","https://openalex.org/W3178291178","https://openalex.org/W3180668190","https://openalex.org/W3191867763","https://openalex.org/W3193426425","https://openalex.org/W3215790634","https://openalex.org/W3216004442","https://openalex.org/W4226167525","https://openalex.org/W4312256083","https://openalex.org/W4312563428","https://openalex.org/W4312605608","https://openalex.org/W4312769060","https://openalex.org/W4312887059","https://openalex.org/W4312999279","https://openalex.org/W4313030842","https://openalex.org/W4313141979","https://openalex.org/W4362009341","https://openalex.org/W4367146742","https://openalex.org/W4382240273","https://openalex.org/W4382468567","https://openalex.org/W4386075772","https://openalex.org/W4386076058","https://openalex.org/W4386083048","https://openalex.org/W4390874575","https://openalex.org/W4393106002","https://openalex.org/W4394625704","https://openalex.org/W4399849389","https://openalex.org/W4400644876","https://openalex.org/W4402125219","https://openalex.org/W4402436199","https://openalex.org/W4402716285","https://openalex.org/W4402980150","https://openalex.org/W4406753732","https://openalex.org/W4411270992","https://openalex.org/W4412081955","https://openalex.org/W4414229358","https://openalex.org/W4414908357","https://openalex.org/W7133184875","https://openalex.org/W7133236640"],"related_works":["https://openalex.org/W3170602832","https://openalex.org/W4313165093","https://openalex.org/W4402980150","https://openalex.org/W4385801165","https://openalex.org/W4409250116","https://openalex.org/W4382450914","https://openalex.org/W4323570449","https://openalex.org/W4382240273","https://openalex.org/W7126020307","https://openalex.org/W4285604209"],"abstract_inverted_index":{"In":[0],"semi-supervised":[1],"object":[2],"detection":[3],"(SSOD),":[4],"due":[5],"to":[6,53,131,171,194],"the":[7,13,34,39,50,58,94,99,105,124,169,173,181,199,218,235,238],"limited":[8],"availability":[9],"of":[10,17,37,41,72,87,176,201],"labeled":[11,232],"data,":[12],"quality":[14,175,205],"and":[15,104,155,220],"quantity":[16],"pseudo":[18,43,100,106,136,177],"labels":[19,44,101,107,139,178,202],"generated":[20,65,179],"from":[21,123],"unlabeled":[22],"images":[23],"are":[24,64,140],"crucial":[25],"for":[26],"model":[27,126],"training.":[28],"Our":[29],"study":[30],"reveals":[31],"that":[32,167],"in":[33,97],"early":[35],"stages":[36],"training,":[38],"number":[40,71],"usable":[42],"is":[45],"very":[46],"low,":[47],"which":[48,91,120],"hampers":[49],"model's":[51,95],"ability":[52],"converge":[54],"quickly.":[55],"Furthermore,":[56],"throughout":[57],"training":[59,145],"process,":[60],"even":[61],"though":[62],"pseudo-labels":[63],"with":[66,127,153,185,203,229],"high":[67],"confidence,":[68],"a":[69,83,113,186],"significant":[70],"labeling":[73],"errors":[74],"still":[75],"occur.":[76],"To":[77],"address":[78],"these":[79],"challenges,":[80],"we":[81,111],"propose":[82],"novel":[84],"framework,":[85],"Generation-to-Optimization":[86],"Pseudo":[88,115],"Labels":[89],"(GO-PL),":[90],"comprehensively":[92],"improves":[93],"performance":[96,212],"both":[98],"generation":[102],"stage":[103],"optimization":[108],"stage.":[109],"Specifically,":[110],"design":[112],"CLIP-based":[114],"Label":[116],"Generation":[117],"(CPLG)":[118],"module,":[119],"matches":[121],"proposals":[122],"teacher":[125,182],"CLIP":[128],"text":[129],"embeddings":[130],"generate":[132],"semantically":[133],"consistent":[134],"high-confidence":[135],"labels.":[137],"These":[138],"further":[141],"integrated":[142],"into":[143],"student":[144],"via":[146],"an":[147],"auxiliary":[148],"loss,":[149],"enabling":[150],"early-stage":[151],"guidance":[152],"stable":[154],"informative":[156],"supervision":[157],"signals.":[158],"We":[159],"also":[160],"introduce":[161],"Pixel-guided":[162],"Instance":[163],"Weighting":[164],"(PIW)":[165],"module":[166],"utilizes":[168],"SAM":[170],"assess":[172],"pixel-level":[174],"by":[180,242],"model.":[183],"Combined":[184],"local":[187],"voting":[188],"mechanism,":[189],"PIW":[190],"dynamically":[191],"assigns":[192],"weights":[193],"each":[195],"pseudo-label,":[196],"thereby":[197],"optimizing":[198],"impact":[200],"varying":[204],"on":[206,213,234],"gradient":[207],"updates.":[208],"GO-PL":[209],"demonstrates":[210],"strong":[211],"standard":[214],"SSOD":[215],"benchmarks,":[216],"including":[217],"MS-COCO":[219],"PASCAL":[221],"VOC":[222],"datasets.":[223],"Notably,":[224],"it":[225],"achieves":[226],"26.7%":[227],"mAP":[228],"only":[230],"1%":[231],"data":[233],"MS-COCO,":[236],"surpassing":[237],"previous":[239],"best":[240],"approach":[241],"1.7%.":[243]},"counts_by_year":[],"updated_date":"2026-09-27T08:07:27.782135","created_date":"2026-09-02T00:00:00"}