{"id":"https://openalex.org/W7225794756","doi":"https://doi.org/10.3390/s26227130","title":"Robust Waste Image Classification Under Class Imbalance and Visual Variability: Weak-to-Strong Learning with Activation-Guided CutMix","display_name":"Robust Waste Image Classification Under Class Imbalance and Visual Variability: Weak-to-Strong Learning with Activation-Guided CutMix","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225794756","doi":"https://doi.org/10.3390/s26227130"},"language":"en","primary_location":{"id":"doi:10.3390/s26227130","doi":"https://doi.org/10.3390/s26227130","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s26227130","pdf_url":null,"source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"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":"Sensors","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/s26227130","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064853881","display_name":"Hyeongjun Jeon","orcid":"https://orcid.org/0000-0001-6091-7951","observed_orcids":["https://orcid.org/0000-0001-6091-7951","https://orcid.org/0009-0008-6129-7043"]},"institutions":[{"id":"https://openalex.org/I120158604","display_name":"Kunsan National University","ror":"https://ror.org/02yj55q56","country_code":"KR","type":"education","lineage":["https://openalex.org/I120158604"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeongjun Jeon","raw_affiliation_strings":["Department of AI Convergence, Kunsan National University, Gunsan-si 54150, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0007-8542-912X","affiliations":[{"raw_affiliation_string":"Department of AI Convergence, Kunsan National University, Gunsan-si 54150, Republic of Korea","institution_ids":["https://openalex.org/I120158604"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031212894","display_name":"Han Byeol Bae","orcid":"https://orcid.org/0000-0002-3004-1001","observed_orcids":["https://orcid.org/0000-0002-3004-1001"]},"institutions":[{"id":"https://openalex.org/I120158604","display_name":"Kunsan National University","ror":"https://ror.org/02yj55q56","country_code":"KR","type":"education","lineage":["https://openalex.org/I120158604"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Han Byeol Bae","raw_affiliation_strings":["Department of AI Convergence, Kunsan National University, Gunsan-si 54150, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-3004-1001","affiliations":[{"raw_affiliation_string":"Department of AI Convergence, Kunsan National University, Gunsan-si 54150, Republic of Korea","institution_ids":["https://openalex.org/I120158604"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5031212894"],"corresponding_institution_ids":["https://openalex.org/I120158604"],"apc_list":{"value":2600,"currency":"CHF","value_usd":3137},"apc_paid":{"value":2600,"currency":"CHF","value_usd":3137},"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":"26","issue":"22","first_page":"7130","last_page":"7130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9937000274658203,"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":0.9937000274658203,"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":0.003800000064074993,"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.0010999999940395355,"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":[],"concepts":[{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6816999912261963},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6791999936103821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.66839998960495},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6654000282287598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6165000200271606},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5379999876022339},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5044999718666077},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38359999656677246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3758000135421753},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/s26227130","doi":"https://doi.org/10.3390/s26227130","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s26227130","pdf_url":null,"source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"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":"Sensors","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/s26227130","doi":"https://doi.org/10.3390/s26227130","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s26227130","pdf_url":null,"source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","jufo-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"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":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automated":[0],"waste":[1],"image":[2],"classification":[3],"remains":[4],"challenging":[5],"because":[6],"of":[7,77,152],"substantial":[8],"class":[9,160],"imbalance,":[10],"large":[11],"intra-class":[12],"visual":[13,18],"variability,":[14],"and":[15,35,43,105,120,140,145,162],"high":[16],"inter-class":[17],"similarity.":[19],"We":[20],"propose":[21],"a":[22],"backbone-agnostic":[23],"weak-to-strong":[24],"training":[25],"framework":[26,89,177],"that":[27],"combines":[28],"class-balanced":[29],"focal":[30],"supervision":[31],"over":[32],"weak,":[33],"strong,":[34],"activation-guided":[36],"mixed":[37],"views,":[38],"asymmetric":[39],"Kullback\u2013Leibler":[40],"(KL)":[41],"consistency,":[42],"Activation-Guided":[44,61],"CutMix.":[45],"The":[46,88,142],"detached":[47],"weak-view":[48],"prediction":[49],"distribution":[50],"serves":[51],"as":[52],"the":[53,57,64,68,78,109,175,179],"reference":[54],"for":[55],"aligning":[56],"strong-view":[58],"prediction,":[59],"while":[60,114],"CutMix":[62],"centers":[63],"replacement":[65],"region":[66],"at":[67],"highest-response":[69],"location":[70,86],"derived":[71],"from":[72],"an":[73],"intermediate":[74],"feature":[75,156],"map":[76],"base":[79],"weak":[80],"view":[81],"rather":[82],"than":[83],"selecting":[84],"its":[85],"randomly.":[87],"was":[90],"evaluated":[91],"on":[92,108,123],"two":[93],"waste-classification":[94],"datasets":[95],"using":[96],"seven":[97],"CNN":[98],"backbones.":[99],"ConvNeXt-Base":[100],"achieved":[101,116],"98.88%":[102],"mean":[103,118],"accuracy":[104,119],"98.44%":[106],"macro-F1":[107,122],"corrected":[110],"Waste":[111],"Classification":[112],"dataset,":[113],"ConvNeXt-Tiny":[115],"79.20%":[117],"76.73%":[121],"WaRP-C.":[124],"Ablation":[125],"studies":[126],"demonstrated":[127],"performance":[128],"gains":[129],"across":[130],"different":[131],"backbone":[132],"architectures,":[133],"with":[134],"component-level":[135],"contributions":[136],"varying":[137],"by":[138],"dataset":[139],"backbone.":[141],"t-SNE,":[143],"confusion-matrix,":[144],"Grad-CAM":[146],"analyses":[147],"provided":[148],"complementary":[149],"qualitative":[150],"evidence":[151],"more":[153,163],"clearly":[154],"organized":[155],"distributions,":[157],"reduced":[158],"off-diagonal":[159],"confusion,":[161],"object-focused":[164],"activation":[165],"patterns.":[166],"Because":[167],"all":[168],"auxiliary":[169],"operations":[170],"are":[171],"confined":[172],"to":[173],"training,":[174],"proposed":[176],"preserves":[178],"original":[180],"single-branch,":[181],"single-forward-pass":[182],"inference":[183],"architecture.":[184]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}