{"id":"https://openalex.org/W7124159659","doi":"https://doi.org/10.1109/tip.2026.3652357","title":"Toward Generative Understanding: Incremental Few-Shot Semantic Segmentation With Diffusion Models","display_name":"Toward Generative Understanding: Incremental Few-Shot Semantic Segmentation With Diffusion Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7124159659","doi":"https://doi.org/10.1109/tip.2026.3652357","pmid":"https://pubmed.ncbi.nlm.nih.gov/41533631"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3652357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3652357","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/A5123033033","display_name":"Qun Li","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qun Li","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-8034-6030","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101716869","display_name":"Lu Huang","orcid":"https://orcid.org/0000-0003-2834-3518"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Huang","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123011613","display_name":"Fu Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu Xiao","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-1815-2793","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123030222","display_name":"Na Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Na Zhao","raw_affiliation_strings":["Information Systems Technology and Design, Singapore University of Technology and Design, Tampines, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-2329-7014","affiliations":[{"raw_affiliation_string":"Information Systems Technology and Design, Singapore University of Technology and Design, Tampines, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059316269","display_name":"B. Bhanu","orcid":null},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bir Bhanu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, Riverside, Riverside, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8971-6416","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Riverside, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":0.06361925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"743","last_page":"758"},"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":0.973800003528595,"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":0.973800003528595,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.004900000058114529,"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/T11448","display_name":"Face recognition and analysis","score":0.0020000000949949026,"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/segmentation","display_name":"Segmentation","score":0.5845999717712402},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5769000053405762},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5708000063896179},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5088000297546387},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48750001192092896},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43970000743865967},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4352000057697296},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.41940000653266907},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.39399999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7827000021934509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6625000238418579},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5845999717712402},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5769000053405762},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5708000063896179},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5088000297546387},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48750001192092896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.41940000653266907},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39410001039505005},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3517000079154968},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3147999942302704},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.30489999055862427},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.2678000032901764},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3652357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3652357","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:41533631","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41533631","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","score":0.7708348035812378,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1748206643","display_name":null,"funder_award_id":"62276143","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2371766950","display_name":null,"funder_award_id":"BK20231287","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G7680777363","display_name":null,"funder_award_id":"62302233","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W1994062553","https://openalex.org/W2010382953","https://openalex.org/W2017745767","https://openalex.org/W2037227137","https://openalex.org/W2144794286","https://openalex.org/W2473930607","https://openalex.org/W2794825826","https://openalex.org/W2796346823","https://openalex.org/W2798836702","https://openalex.org/W2804199516","https://openalex.org/W2924485953","https://openalex.org/W2932083555","https://openalex.org/W2963599420","https://openalex.org/W2965729941","https://openalex.org/W2990230185","https://openalex.org/W2994528761","https://openalex.org/W3011986058","https://openalex.org/W3034435444","https://openalex.org/W3047258141","https://openalex.org/W3108975329","https://openalex.org/W3131068231","https://openalex.org/W4221153269","https://openalex.org/W4288099336","https://openalex.org/W4312901617","https://openalex.org/W4312933868","https://openalex.org/W4386066138","https://openalex.org/W4386075956","https://openalex.org/W4386245957","https://openalex.org/W4387968063","https://openalex.org/W4387969909","https://openalex.org/W4390872876","https://openalex.org/W4391274686","https://openalex.org/W4391827309","https://openalex.org/W4392693600","https://openalex.org/W4393150438","https://openalex.org/W4393853176","https://openalex.org/W4402703098","https://openalex.org/W4402727719","https://openalex.org/W4402753894","https://openalex.org/W4402754105","https://openalex.org/W4402772505","https://openalex.org/W4403233964","https://openalex.org/W4404439849","https://openalex.org/W4409366947","https://openalex.org/W4411245230","https://openalex.org/W4415797983"],"related_works":[],"abstract_inverted_index":{"Incremental":[0],"Few-shot":[1],"Semantic":[2],"Segmentation":[3],"(iFSS)":[4],"aims":[5],"to":[6,64,70,121],"learn":[7],"novel":[8,27,66,82,174],"classes":[9,28,80],"with":[10,135],"limited":[11,62],"samples":[12],"while":[13,50,131],"preserving":[14],"segmentation":[15,219],"capability":[16],"for":[17,90,98],"base":[18,79,172],"classes,":[19,67,175],"addressing":[20],"the":[21,76,91,103,143,168,198],"challenge":[22],"of":[23,26,32,78,163,171],"continual":[24],"learning":[25,77],"and":[29,46,61,81,107,173,183,201,212],"catastrophic":[30,181],"forgetting":[31],"previously":[33],"seen":[34],"classes.":[35,83],"Existing":[36],"methods":[37],"mainly":[38],"rely":[39],"on":[40,123,197],"techniques":[41],"such":[42,57],"as":[43,58],"knowledge":[44],"distillation":[45],"background":[47],"learning,":[48],"which,":[49],"partially":[51],"effective,":[52],"still":[53],"suffer":[54],"from":[55],"issues":[56],"feature":[59,178],"drift":[60],"generalization":[63],"real-world":[65],"primarily":[68],"due":[69],"a":[71,94],"bidirectional":[72],"coupling":[73],"bottleneck":[74],"between":[75,105],"To":[84],"address":[85],"these":[86],"challenges,":[87],"we":[88,101],"propose,":[89],"first":[92],"time,":[93],"diffusion-based":[95],"generative":[96,106],"framework":[97,156],"iFSS.":[99],"Specifically,":[100],"bridge":[102],"gap":[104],"discriminative":[108],"tasks":[109],"through":[110],"an":[111],"innovative":[112],"binary-to-RGB":[113],"mask":[114],"mapping":[115],"mechanism,":[116],"enabling":[117,184],"pre-trained":[118],"diffusion":[119,153],"models":[120],"focus":[122],"target":[124],"regions":[125],"via":[126],"class-specific":[127,164],"semantic":[128,165],"embedding":[129,169],"optimization":[130,162],"sharpening":[132],"foreground-background":[133],"contrast":[134],"color":[136],"embeddings.":[137],"A":[138],"lightweight":[139],"post-processor":[140],"then":[141],"refines":[142],"generated":[144],"images":[145],"into":[146],"high-quality":[147],"binary":[148],"masks.":[149],"Crucially,":[150],"by":[151],"leveraging":[152],"priors,":[154],"our":[155,192],"avoids":[157],"complex":[158],"training":[159],"strategies.":[160],"The":[161],"embeddings":[166],"decouples":[167],"spaces":[170],"inherently":[176],"preventing":[177],"drift,":[179],"mitigating":[180],"forgetting,":[182],"rapid":[185],"novel-class":[186],"adaptation.":[187],"Experimental":[188],"results":[189,215],"show":[190],"that":[191],"method":[193],"achieves":[194],"state-of-the-art":[195],"performance":[196],"PASCAL-":[199],"$5^{i}$":[200],"COCO-":[202],"$20^{i}$":[203],"datasets":[204],"using":[205],"much":[206],"less":[207],"data":[208],"than":[209],"other":[210],"methods,":[211],"exhibiting":[213],"competitive":[214],"in":[216],"cross-domain":[217],"few-shot":[218],"tasks.":[220],"Project":[221],"page:":[222],"https://ifss-diff.github.io/.":[223]},"counts_by_year":[],"updated_date":"2026-01-25T23:04:38.658462","created_date":"2026-01-15T00:00:00"}