{"id":"https://openalex.org/W4408352943","doi":"https://doi.org/10.1109/icassp49660.2025.10887611","title":"Teaching Others Teaches Yourself: Semi-supervised Ensembled Pseudo-labeling Method for Image Classification","display_name":"Teaching Others Teaches Yourself: Semi-supervised Ensembled Pseudo-labeling Method for Image Classification","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352943","doi":"https://doi.org/10.1109/icassp49660.2025.10887611"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5048697154","display_name":"Wentao Lei","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wentao Lei","raw_affiliation_strings":["HKUST(GZ),Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"HKUST(GZ),Guangzhou,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418783","display_name":"Li Liu","orcid":"https://orcid.org/0000-0002-2011-2873"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Liu","raw_affiliation_strings":["HKUST(GZ),Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"HKUST(GZ),Guangzhou,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048697154"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04159112,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.4474000036716461,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.4474000036716461,"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":0.648457407951355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5708552002906799},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5248486995697021},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5001871585845947},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4532049000263214},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3904878795146942},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34544050693511963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.648457407951355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5708552002906799},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5248486995697021},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5001871585845947},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4532049000263214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3904878795146942},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34544050693511963}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2294370754","https://openalex.org/W2808139377","https://openalex.org/W2888888638","https://openalex.org/W2919704931","https://openalex.org/W2962804657","https://openalex.org/W2964137095","https://openalex.org/W3008402854","https://openalex.org/W3018202776","https://openalex.org/W3034368386","https://openalex.org/W3034681942","https://openalex.org/W3117676280","https://openalex.org/W3164768191","https://openalex.org/W3174697615","https://openalex.org/W3180562345","https://openalex.org/W3182493068","https://openalex.org/W3204273936","https://openalex.org/W3214911933","https://openalex.org/W3216549632","https://openalex.org/W4313307856","https://openalex.org/W4318677156","https://openalex.org/W4372260034","https://openalex.org/W4386804465","https://openalex.org/W6733814495","https://openalex.org/W6758779121","https://openalex.org/W6764051988","https://openalex.org/W6780236752","https://openalex.org/W6780688020","https://openalex.org/W6810719784"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4224009465","https://openalex.org/W4306674287","https://openalex.org/W4286629047","https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W2546503577"],"abstract_inverted_index":{"Semi-supervised":[0],"methods":[1],"have":[2],"recently":[3],"received":[4],"significant":[5,48],"attention":[6],"in":[7],"deep":[8],"learning":[9],"because":[10],"they":[11],"are":[12,107,133],"able":[13],"to":[14,50,81,94,120,135],"reduce":[15],"the":[16,42,51,69,75,96,117,121,137],"dependence":[17],"on":[18,109],"labeled":[19],"data":[20],"while":[21],"ensuring":[22],"good":[23],"performance.":[24],"The":[25],"pseudo-label":[26],"based":[27],"method":[28,37,93,119],"has":[29],"been":[30],"widely":[31],"used":[32],"as":[33],"a":[34,88],"classic":[35],"semi-supervised":[36,63,124],"but":[38],"still":[39],"suffers":[40],"from":[41],"confirmation":[43],"bias":[44],"problem,":[45,58],"which":[46,65],"causes":[47],"damage":[49],"model\u2019s":[52],"training":[53],"process.":[54],"To":[55],"solve":[56],"this":[57],"we":[59,85],"propose":[60],"an":[61],"ensembled":[62],"framework,":[64],"can":[66],"effectively":[67],"improve":[68],"quality":[70],"of":[71,78,116,139],"pseudo-labels":[72],"by":[73],"ensembling":[74,103],"prediction":[76],"results":[77,132],"multiple":[79],"models":[80,100],"generate":[82],"pseudo-labels.":[83],"Simultaneously,":[84],"innovatively":[86],"design":[87],"Ensembled":[89],"Divergence":[90],"Promotion":[91],"(EDP)":[92],"increase":[95],"diversity":[97],"among":[98],"different":[99],"for":[101],"better":[102],"results.":[104],"Extensive":[105],"experiments":[106,129],"conducted":[108,134],"CIFAR-10":[110],"and":[111,130],"CIFAR-100,":[112],"showing":[113],"superior":[114],"performance":[115],"proposed":[118],"state-of-the-art":[122],"(SOTA)":[123],"method.":[125,141],"Meanwhile,":[126],"extensive":[127],"ablation":[128],"visualization":[131],"prove":[136],"effectiveness":[138],"our":[140]},"counts_by_year":[],"updated_date":"2026-02-26T08:16:20.718346","created_date":"2025-10-10T00:00:00"}