{"id":"https://openalex.org/W7135091844","doi":"https://doi.org/10.1109/tip.2026.3671661","title":"LearnMat: Semantic-Aware Self-Supervision Fine-Grained Visual Recognition","display_name":"LearnMat: Semantic-Aware Self-Supervision Fine-Grained Visual Recognition","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7135091844","doi":"https://doi.org/10.1109/tip.2026.3671661","pmid":"https://pubmed.ncbi.nlm.nih.gov/41817981"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3671661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3671661","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,"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"},"type":"article","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/A5057569405","display_name":"Shengling Li","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuaiheng Li","raw_affiliation_strings":["Department of Information Science and Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Science and Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128846965","display_name":"Qing Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]},{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]},{"id":"https://openalex.org/I4210135175","display_name":"Hefei Institute of Technology Innovation","ror":"https://ror.org/044wmmj34","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210135175"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Cai","raw_affiliation_strings":["Innovation School of Artificial Intelligence, Hefei University of Technology, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-8320-6156","affiliations":[{"raw_affiliation_string":"Innovation School of Artificial Intelligence, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422","https://openalex.org/I39774598","https://openalex.org/I4210135175"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fan Zhang","orcid":"https://orcid.org/0000-0002-2478-4722"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Fan Zhang","raw_affiliation_strings":["Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-2478-4722","affiliations":[{"raw_affiliation_string":"Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005217555","display_name":"Yangyang Shu","orcid":"https://orcid.org/0000-0001-6319-6037"},"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":false,"raw_author_name":"Yangyang Shu","raw_affiliation_strings":["School of Systems and Computing, University of New South Wales, Canberra, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Systems and Computing, University of New South Wales, Canberra, Australia","institution_ids":["https://openalex.org/I188329596","https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128803628","display_name":"Guanbin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanbin Li","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4805-0926","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128891569","display_name":"Junyu Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyu Dong","raw_affiliation_strings":["Department of Information Science and Engineering, Ocean University of China, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-7012-2087","affiliations":[{"raw_affiliation_string":"Department of Information Science and Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128906127","display_name":"Lingqiao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lingqiao Liu","raw_affiliation_strings":["School of Computer Science, The University of Adelaide, Adelaide, SA, Australia"],"raw_orcid":"https://orcid.org/0000-0003-3584-795X","affiliations":[{"raw_affiliation_string":"School of Computer Science, The University of Adelaide, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":null,"display_name":"David Zhang","orcid":"https://orcid.org/0000-0002-5027-5286"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"David Zhang","raw_affiliation_strings":["School of Data Science, The Chinese University of Hong Kong, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-5027-5286","affiliations":[{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25188799,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"2555","last_page":"2569"},"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":0.2547000050544739,"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":0.2547000050544739,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.19220000505447388,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.14560000598430634,"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/image-processing","display_name":"Image processing","score":0.44699999690055847},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3869999945163727},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3621000051498413},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3522000014781952},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.32589998841285706},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.3142000138759613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6166999936103821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.595300018787384},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5565000176429749},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.44699999690055847},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3621000051498413},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33719998598098755},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3142000138759613},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3077000081539154},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.2669000029563904},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.25459998846054077}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3671661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3671661","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,"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:41817981","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41817981","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,"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":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4253975749015808}],"awards":[{"id":"https://openalex.org/G3006348383","display_name":null,"funder_award_id":"62471448","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3298737857","display_name":null,"funder_award_id":"62102338","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3642534211","display_name":null,"funder_award_id":"ZR2024YQ004","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G4882631968","display_name":null,"funder_award_id":"tsqn202312109","funder_id":"https://openalex.org/F4320326185","funder_display_name":"Taishan Scholar Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320326185","display_name":"Taishan Scholar Foundation of Shandong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W190927549","https://openalex.org/W1821462560","https://openalex.org/W1954152232","https://openalex.org/W1965555277","https://openalex.org/W2013873417","https://openalex.org/W2069440689","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2138011018","https://openalex.org/W2194775991","https://openalex.org/W2250384498","https://openalex.org/W2398118205","https://openalex.org/W2533598788","https://openalex.org/W2583567407","https://openalex.org/W2606128082","https://openalex.org/W2885613075","https://openalex.org/W2948437274","https://openalex.org/W2951464224","https://openalex.org/W2962858109","https://openalex.org/W2965318645","https://openalex.org/W2990495699","https://openalex.org/W3000388098","https://openalex.org/W3005359536","https://openalex.org/W3024152176","https://openalex.org/W3035524453","https://openalex.org/W3035725276","https://openalex.org/W3096719817","https://openalex.org/W3102046303","https://openalex.org/W3119160127","https://openalex.org/W3124804470","https://openalex.org/W3133008479","https://openalex.org/W3160314846","https://openalex.org/W3168796319","https://openalex.org/W3171007011","https://openalex.org/W3172424021","https://openalex.org/W3175156984","https://openalex.org/W3176087273","https://openalex.org/W3176276772","https://openalex.org/W3194454787","https://openalex.org/W3213192039","https://openalex.org/W3215397687","https://openalex.org/W4221092307","https://openalex.org/W4312235460","https://openalex.org/W4312295999","https://openalex.org/W4312629998","https://openalex.org/W4312823383","https://openalex.org/W4312939067","https://openalex.org/W4313056800","https://openalex.org/W4313156423","https://openalex.org/W4321021073","https://openalex.org/W4360993849","https://openalex.org/W4386057714","https://openalex.org/W4386057726","https://openalex.org/W4386076260","https://openalex.org/W4386352883","https://openalex.org/W4388145471","https://openalex.org/W4389262655","https://openalex.org/W4391697001","https://openalex.org/W4392172801","https://openalex.org/W4392208008","https://openalex.org/W4392968603","https://openalex.org/W4394699135","https://openalex.org/W4396585666","https://openalex.org/W4401024647","https://openalex.org/W4401931559","https://openalex.org/W4403390485","https://openalex.org/W4404672270","https://openalex.org/W4410342729","https://openalex.org/W4411232024","https://openalex.org/W4411244874","https://openalex.org/W4412030570","https://openalex.org/W4413144897","https://openalex.org/W4414198362","https://openalex.org/W4415970869","https://openalex.org/W7138084268"],"related_works":[],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,13,77],"has":[2],"shown":[3],"potential":[4,62],"in":[5,33,56,63],"fine-grained":[6,175],"visual":[7,46],"recognition":[8],"(FGVR).":[9],"However,":[10],"existing":[11,40],"self-supervised":[12,64,76,140],"methods":[14],"are":[15],"often":[16],"susceptible":[17],"to":[18,27,36,145,158],"irrelevant":[19,84],"patterns":[20],"during":[21,95],"training":[22,141],"and":[23,87,91,109,142,162,170,173],"lack":[24],"the":[25,29,49,104,110,116,149,155],"ability":[26],"capture":[28],"critical":[30],"subtle":[31,92,160],"differences":[32,161],"FGVR,":[34],"leading":[35],"suboptimal":[37],"performance.":[38],"Moreover,":[39],"approaches":[41],"focus":[42],"primarily":[43],"on":[44],"uni-modal":[45],"concepts.":[47],"Despite":[48],"emergence":[50],"of":[51,100,129],"powerful":[52],"vision-language":[53],"models":[54],"(VLMs)":[55],"various":[57],"high-level":[58],"vision":[59],"tasks,":[60],"their":[61],"FGVR":[65,182],"remains":[66],"largely":[67],"unexplored.":[68],"To":[69],"this":[70],"end,":[71],"we":[72,118],"propose":[73],"a":[74,120,127],"novel":[75,121],"(LearnMat)":[78],"framework,":[79],"that":[80,134,185],"effectively":[81],"filters":[82],"out":[83],"feature":[85],"interference":[86],"extracts":[88],"more":[89],"important":[90],"discriminative":[93,165],"features":[94],"training.":[96],"Specifically,":[97],"LearnMat":[98,186],"consists":[99],"two":[101],"key":[102,164],"modules:":[103],"semantic":[105,123,137],"awareness":[106],"module":[107,113],"(SAM)":[108],"insight":[111],"extraction":[112],"(IEM).":[114],"In":[115],"SAM,":[117],"introduce":[119],"vision-language-grounded":[122],"distillation":[124],"strategy":[125],"using":[126],"corpus":[128],"generic,":[130],"category-agnostic":[131],"textual":[132],"attributes,":[133],"injects":[135],"explicit":[136],"constraints":[138],"into":[139],"improves":[143],"robustness":[144],"background":[146],"interference.":[147],"Complementarily,":[148],"IEM":[150],"exploits":[151],"gradient-based":[152],"signals":[153],"from":[154],"input":[156],"image":[157],"highlight":[159],"localize":[163],"regions,":[166],"mitigating":[167],"inter-class":[168],"similarity":[169],"intra-class":[171],"variation,":[172],"enhancing":[174],"discrimination.":[176],"Extensive":[177],"experiments":[178],"across":[179],"multiple":[180],"popular":[181],"datasets":[183],"show":[184],"significantly":[187],"outperforms":[188],"recent":[189],"state-of-the-art":[190],"methods,":[191],"highlighting":[192],"its":[193],"marked":[194],"effectiveness.":[195],"Our":[196],"code":[197],"is":[198],"avaliable":[199],"at":[200],"https://github.com/Heng-CHY/LearnMat.":[201]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-03-13T00:00:00"}