{"id":"https://openalex.org/W4286837396","doi":"https://doi.org/10.1109/tip.2022.3176130","title":"CKDF: Cascaded Knowledge Distillation Framework for Robust Incremental Learning","display_name":"CKDF: Cascaded Knowledge Distillation Framework for Robust Incremental Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4286837396","doi":"https://doi.org/10.1109/tip.2022.3176130","pmid":"https://pubmed.ncbi.nlm.nih.gov/35609094"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2022.3176130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3176130","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/A5023566199","display_name":"Kunchi Li","orcid":"https://orcid.org/0000-0001-9874-3571"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kunchi Li","raw_affiliation_strings":["National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9874-3571","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063979916","display_name":"Jun Wan","orcid":"https://orcid.org/0000-0002-4735-2885"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wan","raw_affiliation_strings":["National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4735-2885","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100759691","display_name":"Shan Yu","orcid":"https://orcid.org/0000-0002-9008-6658"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Yu","raw_affiliation_strings":["National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9008-6658","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS), Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0609,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.94523491,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"3825","last_page":"3837"},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9952999949455261,"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/T12676","display_name":"Machine Learning and ELM","score":0.9908000230789185,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7771391868591309},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7705657482147217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6953359842300415},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5761654376983643},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5359049439430237},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5257024765014648},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5165099501609802},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47476935386657715},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.44269508123397827},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42478105425834656},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07658275961875916}],"concepts":[{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7771391868591309},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7705657482147217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6953359842300415},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5761654376983643},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5359049439430237},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5257024765014648},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5165099501609802},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47476935386657715},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.44269508123397827},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42478105425834656},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07658275961875916},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2022.3176130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2022.3176130","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:35609094","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35609094","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[{"id":"https://openalex.org/G1216156006","display_name":null,"funder_award_id":"173211KYSB20200021","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G493081447","display_name":null,"funder_award_id":"2017YFA0105203","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6871481020","display_name":null,"funder_award_id":"U21A20515","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8224262710","display_name":null,"funder_award_id":"XDB32040200","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1682403713","https://openalex.org/W1821462560","https://openalex.org/W2037979274","https://openalex.org/W2117539524","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2473930607","https://openalex.org/W2560647685","https://openalex.org/W2583761661","https://openalex.org/W2771964490","https://openalex.org/W2786446225","https://openalex.org/W2791091755","https://openalex.org/W2884282566","https://openalex.org/W2895699061","https://openalex.org/W2902456977","https://openalex.org/W2902625698","https://openalex.org/W2948734064","https://openalex.org/W2949995560","https://openalex.org/W2954929116","https://openalex.org/W2962707369","https://openalex.org/W2963072899","https://openalex.org/W2963588172","https://openalex.org/W2963788399","https://openalex.org/W2964048876","https://openalex.org/W2964067969","https://openalex.org/W2964189064","https://openalex.org/W2967821093","https://openalex.org/W2995139074","https://openalex.org/W3013325675","https://openalex.org/W3030364939","https://openalex.org/W3035342403","https://openalex.org/W3094314265","https://openalex.org/W3094953068","https://openalex.org/W3098511564","https://openalex.org/W3105913416","https://openalex.org/W3118608800","https://openalex.org/W3144281354","https://openalex.org/W3173553047","https://openalex.org/W3175853876","https://openalex.org/W3176779063","https://openalex.org/W4205363273","https://openalex.org/W4211061250","https://openalex.org/W4214924370","https://openalex.org/W4287823067","https://openalex.org/W4304149893","https://openalex.org/W6677258307","https://openalex.org/W6732467815","https://openalex.org/W6736334413","https://openalex.org/W6741087337","https://openalex.org/W6741217325","https://openalex.org/W6746643698","https://openalex.org/W6756754374","https://openalex.org/W6757384668","https://openalex.org/W6779133958","https://openalex.org/W6784399590","https://openalex.org/W6784940669","https://openalex.org/W6795846790","https://openalex.org/W6803966525"],"related_works":["https://openalex.org/W3026162553","https://openalex.org/W2062195135","https://openalex.org/W2768175398","https://openalex.org/W2344382886","https://openalex.org/W2905271011","https://openalex.org/W3164948662","https://openalex.org/W4289536128","https://openalex.org/W3153597579","https://openalex.org/W1872833176","https://openalex.org/W4309346246"],"abstract_inverted_index":{"Recently,":[0],"owing":[1],"to":[2,46,118,123,135,159,167,187,191,216,219,282],"the":[3,11,30,42,47,56,60,64,69,73,88,92,97,108,120,125,130,137,144,164,169,173,201,221,225,229,239,244,255,259,271],"superior":[4],"performances,":[5],"knowledge":[6,40,90,122,223,237,245],"distillation-based":[7],"(kd-based)":[8],"methods":[9,79],"with":[10],"exemplar":[12],"rehearsal":[13,157],"have":[14,181],"been":[15],"widely":[16],"applied":[17,281],"in":[18,77,96,100,148],"class":[19],"incremental":[20],"learning":[21,51,249],"(CIL).":[22],"However,":[23],"we":[24,86,150,199,268],"discover":[25],"that":[26,270,278,289],"they":[27],"suffer":[28],"from":[29,41,91,238],"feature":[31,61,109,126,177,260],"uncalibration":[32],"problem,":[33,107],"which":[34,115],"is":[35,83,113,116,214,232,274],"caused":[36,142],"by":[37,143,162,235],"directly":[38,95],"transferring":[39,236],"old":[43,57,93,131,226],"model":[44,49,58,94,231,242],"immediately":[45],"new":[48,53,67,230,250,256],"when":[50],"a":[52,152,275],"task.":[54],"As":[55,176],"confuses":[59],"representations":[62],"between":[63],"learned":[65],"and":[66,72,248],"classes,":[68],"kd":[70],"loss":[71,75],"classification":[74],"used":[76,117,215],"kd-based":[78,102,284],"are":[80,265],"heterogeneous.":[81],"This":[82],"detrimental":[84],"if":[85],"learn":[87],"existing":[89,121,222],"way":[98],"as":[99],"typical":[101],"methods.":[103,285],"To":[104],"tackle":[105],"this":[106,184],"calibration":[110],"network":[111],"(FCN)":[112],"proposed,":[114],"calibrate":[119,220],"alleviate":[124],"representation":[127],"confusion":[128],"of":[129,140,172,179,224,262],"model.":[132,227],"In":[133],"addition,":[134],"relieve":[136],"task-recency":[138],"bias":[139],"FCN":[141,161,218],"limited":[145],"storage":[146],"memory":[147,165],"CIL,":[149],"propose":[151,200],"novel":[153],"image-feature":[154],"hybrid":[155],"sample":[156],"strategy":[158,247],"train":[160,192,217],"splitting":[163],"budget":[166],"store":[168,188],"image-and-feature":[170],"exemplars":[171,261],"previous":[174,263],"tasks.":[175],"embeddings":[178],"images":[180],"much":[182],"lower-dimensions,":[183],"allows":[185],"us":[186],"more":[189],"samples":[190],"FCN.":[193],"Based":[194],"on":[195,295],"these":[196],"two":[197],"improvements,":[198],"Cascaded":[202],"Knowledge":[203],"Distillation":[204],"Framework":[205],"(CKDF)":[206],"including":[207],"three":[208],"main":[209],"stages.":[210],"The":[211],"first":[212],"stage":[213],"Then,":[228],"trained":[233],"simultaneously":[234],"calibrated":[240],"teacher":[241],"through":[243],"distillation":[246],"classes.":[251],"Finally,":[252],"after":[253],"completing":[254],"task":[257],"learning,":[258],"tasks":[264],"updated.":[266],"Importantly,":[267],"demonstrate":[269],"proposed":[272],"CKDF":[273],"general":[276],"framework":[277],"can":[279],"be":[280],"various":[283],"Experimental":[286],"results":[287],"show":[288],"our":[290],"method":[291],"achieves":[292],"state-of-the-art":[293],"performances":[294],"several":[296],"CIL":[297],"benchmarks.":[298]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}