{"id":"https://openalex.org/W4414408711","doi":"https://doi.org/10.3390/make7030107","title":"Saliency-Guided Local Semantic Mixing for Long-Tailed Image Classification","display_name":"Saliency-Guided Local Semantic Mixing for Long-Tailed Image Classification","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4414408711","doi":"https://doi.org/10.3390/make7030107"},"language":"en","primary_location":{"id":"doi:10.3390/make7030107","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7030107","pdf_url":"https://www.mdpi.com/2504-4990/7/3/107/pdf?version=1758544478","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-4990/7/3/107/pdf?version=1758544478","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiahui Lv","orcid":"https://orcid.org/0009-0001-3214-0310"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahui Lv","raw_affiliation_strings":["Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410073, China"],"raw_orcid":"https://orcid.org/0009-0001-3214-0310","affiliations":[{"raw_affiliation_string":"Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100771450","display_name":"Jun Lei","orcid":"https://orcid.org/0000-0002-8031-5461"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Lei","raw_affiliation_strings":["Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091973566","display_name":"Jun Zhang","orcid":"https://orcid.org/0000-0003-1804-9198"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Zhang","raw_affiliation_strings":["Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410073, China"],"raw_orcid":"https://orcid.org/0000-0003-1804-9198","affiliations":[{"raw_affiliation_string":"Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763730","display_name":"Chao Chen","orcid":"https://orcid.org/0000-0001-9272-7618"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Chen","raw_affiliation_strings":["Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410073, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101919384","display_name":"Shuohao Li","orcid":"https://orcid.org/0000-0003-4958-8573"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuohao Li","raw_affiliation_strings":["Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410073, China"],"raw_orcid":"https://orcid.org/0000-0003-4958-8573","affiliations":[{"raw_affiliation_string":"Laboratory for Big Data and Decision, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101919384"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22194818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":"3","first_page":"107","last_page":"107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9986000061035156,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9986000061035156,"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/T11659","display_name":"Advanced Image Fusion Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.9977999925613403,"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/discriminative-model","display_name":"Discriminative model","score":0.630299985408783},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5924000144004822},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5080999732017517},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4702000021934509},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4602999985218048},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.42730000615119934},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4032000005245209},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3813000023365021},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.37619999051094055}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.630299985408783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6205999851226807},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.616100013256073},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5924000144004822},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5080999732017517},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4702000021934509},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4235000014305115},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4032000005245209},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C123860398","wikidata":"https://www.wikidata.org/wiki/Q6934605","display_name":"Multiclass classification","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25850000977516174}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/make7030107","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7030107","pdf_url":"https://www.mdpi.com/2504-4990/7/3/107/pdf?version=1758544478","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b05a23e36a4342a1b64f224ab38d6c2d","is_oa":true,"landing_page_url":"https://doaj.org/article/b05a23e36a4342a1b64f224ab38d6c2d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning and Knowledge Extraction, Vol 7, Iss 3, p 107 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/make7030107","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make7030107","pdf_url":"https://www.mdpi.com/2504-4990/7/3/107/pdf?version=1758544478","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324150","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414408711.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2040271314","https://openalex.org/W2111741784","https://openalex.org/W2117539524","https://openalex.org/W2136903812","https://openalex.org/W2148143831","https://openalex.org/W2168809519","https://openalex.org/W2194775991","https://openalex.org/W2476548250","https://openalex.org/W2592929672","https://openalex.org/W2618530766","https://openalex.org/W2767106145","https://openalex.org/W2797977484","https://openalex.org/W2962858109","https://openalex.org/W2962933664","https://openalex.org/W2963351448","https://openalex.org/W2963691377","https://openalex.org/W2963703197","https://openalex.org/W2970941190","https://openalex.org/W3034601242","https://openalex.org/W3035552357","https://openalex.org/W3044057088","https://openalex.org/W3108105109","https://openalex.org/W3128945844","https://openalex.org/W3163842339","https://openalex.org/W3175613352","https://openalex.org/W3176474016","https://openalex.org/W3177200443","https://openalex.org/W3179096061","https://openalex.org/W3203770998","https://openalex.org/W3215720729","https://openalex.org/W4287812705","https://openalex.org/W4307823382","https://openalex.org/W4312244159","https://openalex.org/W4312866014","https://openalex.org/W4319339239","https://openalex.org/W4365451524","https://openalex.org/W4378417908","https://openalex.org/W4384666235","https://openalex.org/W4385767961","https://openalex.org/W4385801322","https://openalex.org/W4386065770","https://openalex.org/W4387587692","https://openalex.org/W4390873567","https://openalex.org/W4391473819","https://openalex.org/W4393154132","https://openalex.org/W4408278904"],"related_works":[],"abstract_inverted_index":{"In":[0,24],"real-world":[1],"visual":[2],"recognition":[3],"tasks,":[4],"long-tailed":[5,150,171],"distributions":[6,152],"pose":[7],"a":[8,104],"widespread":[9],"challenge,":[10],"with":[11,192],"extreme":[12],"class":[13],"imbalance":[14],"severely":[15],"limiting":[16],"the":[17,47,76,79,90,95,128,184],"representational":[18],"learning":[19],"capability":[20],"of":[21,49,78,94,132,149],"deep":[22,30],"models.":[23],"practice,":[25],"due":[26],"to":[27,139],"this":[28,42,100,164],"imbalance,":[29],"models":[31,195],"often":[32],"exhibit":[33],"poor":[34],"generalization":[35],"performance":[36,199],"on":[37,75],"tail":[38,68,133],"classes.":[39],"To":[40,98],"address":[41],"issue,":[43],"data":[44,151],"augmentation":[45],"through":[46],"synthesis":[48],"new":[50],"tail-class":[51,142],"samples":[52],"has":[53],"become":[54],"an":[55],"effective":[56],"method.":[57],"One":[58],"popular":[59],"approach":[60],"is":[61,187],"CutMix,":[62],"which":[63,111],"explicitly":[64],"mixes":[65],"images":[66],"from":[67,82],"and":[69,116,135,153,180,196],"other":[70],"classes,":[71],"constructing":[72],"labels":[73,87,138],"based":[74],"ratio":[77],"regions":[80],"cropped":[81],"both":[83],"images.":[84],"However,":[85],"region-based":[86],"completely":[88],"ignore":[89],"inherent":[91],"semantic":[92,107],"information":[93],"augmented":[96],"samples.":[97,143],"overcome":[99],"problem,":[101],"we":[102],"propose":[103],"saliency-guided":[105],"local":[106,118],"mixing":[108,119],"(LSM)":[109],"method,":[110],"uses":[112],"differentiable":[113],"block":[114],"decoupling":[115],"semantic-aware":[117],"techniques.":[120],"This":[121,144],"method":[122,165],"integrates":[123],"head-class":[124],"backgrounds":[125],"while":[126],"preserving":[127],"key":[129],"discriminative":[130],"features":[131],"classes":[134],"dynamically":[136],"assigns":[137],"effectively":[140],"augment":[141],"results":[145],"in":[146,156],"efficient":[147],"balancing":[148],"significant":[154,167,198],"improvements":[155],"classification":[157,175,194],"performance.":[158],"The":[159],"experimental":[160],"validation":[161],"shows":[162],"that":[163],"demonstrates":[166],"advantages":[168],"across":[169],"three":[170],"benchmark":[172],"datasets,":[173],"improving":[174],"accuracy":[176],"by":[177],"5.0%,":[178],"7.3%,":[179],"6.1%,":[181],"respectively.":[182],"Notably,":[183],"LSM":[185],"framework":[186],"highly":[188],"compatible,":[189],"seamlessly":[190],"integrating":[191],"existing":[193],"providing":[197],"gains,":[200],"validating":[201],"its":[202],"broad":[203],"applicability.":[204]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}