{"id":"https://openalex.org/W3042615550","doi":"https://doi.org/10.1109/tip.2020.3011269","title":"Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering","display_name":"Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3042615550","doi":"https://doi.org/10.1109/tip.2020.3011269","mag":"3042615550"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2020.3011269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.3011269","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.09990","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wonjik Kim","orcid":"https://orcid.org/0000-0003-1067-8096"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Wonjik Kim","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Tokyo, Japan","Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1067-8096","affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Asako Kanezaki","orcid":"https://orcid.org/0000-0003-3217-1405"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Asako Kanezaki","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Tokyo, Japan","Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3217-1405","affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":null,"display_name":"Masayuki Tanaka","orcid":"https://orcid.org/0000-0002-5756-1904"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Tanaka","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology, Tokyo, Japan","Tokyo Institute of Technology, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5756-1904","affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Tokyo Institute of Technology, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.6498,"has_fulltext":false,"cited_by_count":249,"citation_normalized_percentile":{"value":0.99070029,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"8055","last_page":"8068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.5347999930381775,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.5347999930381775,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.15449999272823334,"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":0.020600000396370888,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.7649999856948853},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6434999704360962},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.6269999742507935},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.5637000203132629},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5084999799728394},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.5027999877929688},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.45570001006126404},{"id":"https://openalex.org/keywords/range-segmentation","display_name":"Range segmentation","score":0.45100000500679016},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4359999895095825}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7954000234603882},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7649999856948853},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6434999704360962},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6269999742507935},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.5637000203132629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5551999807357788},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5084999799728394},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.5027999877929688},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.45570001006126404},{"id":"https://openalex.org/C67561299","wikidata":"https://www.wikidata.org/wiki/Q7292710","display_name":"Range segmentation","level":5,"score":0.45100000500679016},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4359999895095825},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.43209999799728394},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3652999997138977},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3492000102996826},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3181999921798706},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.2653000056743622},{"id":"https://openalex.org/C42314347","wikidata":"https://www.wikidata.org/wiki/Q6865488","display_name":"Minimum spanning tree-based segmentation","level":5,"score":0.26460000872612}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2020.3011269","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2020.3011269","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":"pmh:oai:arXiv.org:2007.09990","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.09990","pdf_url":"https://arxiv.org/pdf/2007.09990","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.09990","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.09990","pdf_url":"https://arxiv.org/pdf/2007.09990","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7261574119","display_name":"A Study on Deep Learning of Unsupervised Image Segmentation by Differentiable Clustering","funder_award_id":"20K19837","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1507506748","https://openalex.org/W1783315696","https://openalex.org/W1903029394","https://openalex.org/W1909952827","https://openalex.org/W1948751323","https://openalex.org/W1964884769","https://openalex.org/W1999478155","https://openalex.org/W2002260165","https://openalex.org/W2027693089","https://openalex.org/W2035773017","https://openalex.org/W2037227137","https://openalex.org/W2046382188","https://openalex.org/W2048074730","https://openalex.org/W2086052791","https://openalex.org/W2110158442","https://openalex.org/W2114650767","https://openalex.org/W2118246710","https://openalex.org/W2120480077","https://openalex.org/W2121189958","https://openalex.org/W2124592697","https://openalex.org/W2130325614","https://openalex.org/W2148852318","https://openalex.org/W2154644822","https://openalex.org/W2169551590","https://openalex.org/W2203062554","https://openalex.org/W2216125271","https://openalex.org/W2293194425","https://openalex.org/W2337429362","https://openalex.org/W2519610629","https://openalex.org/W2533218643","https://openalex.org/W2566871317","https://openalex.org/W2776732561","https://openalex.org/W2799124825","https://openalex.org/W2801780873","https://openalex.org/W2887420797","https://openalex.org/W2963198662","https://openalex.org/W2963687373","https://openalex.org/W2963881378","https://openalex.org/W2964234847","https://openalex.org/W2972093541","https://openalex.org/W2990500698","https://openalex.org/W6631943919","https://openalex.org/W6638667902","https://openalex.org/W6640295612","https://openalex.org/W6662978298","https://openalex.org/W6676060660","https://openalex.org/W6676071220","https://openalex.org/W6678914141","https://openalex.org/W6679854563","https://openalex.org/W6681644649","https://openalex.org/W6685380521","https://openalex.org/W6745842894"],"related_works":[],"abstract_inverted_index":{"The":[0,160,260],"usage":[1],"of":[2,49,99,122,139,151,162,174,180,201,214,240,262,272],"convolutional":[3],"neural":[4],"networks":[5,249],"(CNNs)":[6],"for":[7,186,218],"unsupervised":[8,38,175],"image":[9,19,39,58,176,245,273],"segmentation":[10,177,219,246],"was":[11,266],"investigated":[12],"in":[13],"this":[14,163],"study.":[15],"Similar":[16],"to":[17,26,32,92,146],"supervised":[18],"segmentation,":[20,40],"the":[21,30,34,61,76,80,94,105,115,120,133,137,156,199,215,241,258,263],"proposed":[22,81,134,216,242,264],"CNN":[23],"assigns":[24],"labels":[25,48,63,124],"pixels":[27,50,98,111],"that":[28,154,178,197],"denote":[29],"cluster":[31],"which":[33,225],"pixel":[35,62],"belongs.":[36],"In":[37,79],"however,":[41],"no":[42],"training":[43],"images":[44,255],"or":[45],"ground":[46],"truth":[47],"are":[51,67,73,89,131,165],"specified":[52],"beforehand.":[53],"Therefore,":[54],"once":[55],"a":[56,148,170,192,252],"target":[57],"is":[59],"input,":[60,224],"and":[64,70,85,118,142,182],"feature":[65],"representations":[66],"jointly":[68],"optimized,":[69],"their":[71],"parameters":[72],"updated":[74],"by":[75,206,247],"gradient":[77],"descent.":[78],"approach,":[82],"label":[83,152],"prediction":[84],"network":[86,173],"parameter":[87],"learning":[88],"alternately":[90],"iterated":[91],"meet":[93],"following":[95],"criteria:":[96],"(a)":[97],"similar":[100],"features":[101],"should":[102,112,125],"be":[103,113,126],"assigned":[104,114],"same":[106,116],"label,":[107,117],"(b)":[108],"spatially":[109],"continuous":[110],"(c)":[119],"number":[121],"unique":[123],"large.":[127],"Although":[128],"these":[129],"criteria":[130,158],"incompatible,":[132],"approach":[135,265],"minimizes":[136],"combination":[138],"similarity":[140],"loss":[141,145,195],"spatial":[143,193],"continuity":[144,194],"find":[147],"plausible":[149],"solution":[150],"assignment":[153],"balances":[155],"aforementioned":[157],"well.":[159],"contributions":[161],"study":[164],"four-fold.":[166],"First,":[167],"we":[168,190,210,236],"propose":[169],"novel":[171],"end-to-end":[172],"consists":[179],"normalization":[181],"an":[183,212],"argmax":[184],"function":[185,196],"differentiable":[187],"clustering.":[188],"Second,":[189],"introduce":[191,237],"mitigates":[198],"limitations":[200],"fixed":[202],"segment":[203],"boundaries":[204],"possessed":[205],"previous":[207],"work.":[208],"Third,":[209],"present":[211],"extension":[213,239],"method":[217],"with":[220,251],"scribbles":[221],"as":[222],"user":[223],"showed":[226],"better":[227],"accuracy":[228],"than":[229],"existing":[230],"methods":[231],"while":[232],"maintaining":[233],"efficiency.":[234],"Finally,":[235],"another":[238],"method:":[243],"unseen":[244],"using":[248],"pre-trained":[250],"few":[253],"reference":[254],"without":[256],"re-training":[257],"networks.":[259],"effectiveness":[261],"examined":[267],"on":[268],"several":[269],"benchmark":[270],"datasets":[271],"segmentation.":[274]},"counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":47},{"year":2024,"cited_by_count":53},{"year":2023,"cited_by_count":66},{"year":2022,"cited_by_count":49},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2020-07-23T00:00:00"}