{"id":"https://openalex.org/W3045909231","doi":"https://doi.org/10.48550/arxiv.2007.15124","title":"Foveation for Segmentation of Ultra-High Resolution Images","display_name":"Foveation for Segmentation of Ultra-High Resolution Images","publication_year":2020,"publication_date":"2020-07-29","ids":{"openalex":"https://openalex.org/W3045909231","doi":"https://doi.org/10.48550/arxiv.2007.15124","mag":"3045909231"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2007.15124","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.15124","pdf_url":"https://arxiv.org/pdf/2007.15124","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.15124","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jin, Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064157732","display_name":"Ryutaro Tanno","orcid":"https://orcid.org/0000-0002-8107-6730","observed_orcids":["https://orcid.org/0000-0002-8107-6730"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tanno, Ryutaro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073094674","display_name":"Moucheng Xu","orcid":"https://orcid.org/0000-0003-3368-9871","observed_orcids":["https://orcid.org/0000-0003-3368-9871"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Moucheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091336286","display_name":"Thomy Mertzanidou","orcid":"https://orcid.org/0000-0001-9706-7399","observed_orcids":["https://orcid.org/0000-0001-9706-7399"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mertzanidou, Thomy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033449704","display_name":"Daniel C. Alexander","orcid":"https://orcid.org/0000-0003-2439-350X","observed_orcids":["https://orcid.org/0000-0003-2439-350X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander, Daniel C.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9214000105857849,"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":0.9214000105857849,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.0551999993622303,"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/T11605","display_name":"Visual Attention and Saliency Detection","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"}}],"keywords":[{"id":"https://openalex.org/keywords/foveation","display_name":"foveation","score":0.8299999833106995},{"id":"https://openalex.org/keywords/memory-efficient-segmentation","display_name":"memory-efficient segmentation","score":0.5199999809265137},{"id":"https://openalex.org/keywords/aerial-imagery","display_name":"aerial imagery","score":0.5379999876022339},{"id":"https://openalex.org/keywords/histopathology-image-segmentation","display_name":"histopathology image segmentation","score":0.8610000014305115},{"id":"https://openalex.org/keywords/deepglobe","display_name":"DeepGlobe","score":0.7390000224113464}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8207302093505859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7644141912460327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7456333637237549},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7026751041412354},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.6198043823242188},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6009652614593506},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4644925892353058},{"id":"https://openalex.org/C150627866","wikidata":"https://www.wikidata.org/wiki/Q1076893","display_name":"Field of view","level":2,"score":0.4417649507522583},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.4324303865432739},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37114912271499634}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2007.15124","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.15124","pdf_url":"https://arxiv.org/pdf/2007.15124","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2007.15124","doi":"https://doi.org/10.48550/arxiv.2007.15124","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.15124","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.15124","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.15124","pdf_url":"https://arxiv.org/pdf/2007.15124","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2810537366","display_name":null,"funder_award_id":"EP/M020533/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3953918217","display_name":null,"funder_award_id":"EP/R006032/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1536680647","https://openalex.org/W1677182931","https://openalex.org/W1745334888","https://openalex.org/W1901129140","https://openalex.org/W1910657905","https://openalex.org/W1923697677","https://openalex.org/W1948751323","https://openalex.org/W2102605133","https://openalex.org/W2119717200","https://openalex.org/W2148347694","https://openalex.org/W2242818861","https://openalex.org/W2301358467","https://openalex.org/W2335364074","https://openalex.org/W2340897893","https://openalex.org/W2342277278","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2560023338","https://openalex.org/W2563705555","https://openalex.org/W2565639579","https://openalex.org/W2602076750","https://openalex.org/W2603429625","https://openalex.org/W2609402060","https://openalex.org/W2737682710","https://openalex.org/W2752013927","https://openalex.org/W2767002724","https://openalex.org/W2785934082","https://openalex.org/W2804199516","https://openalex.org/W2884822772","https://openalex.org/W2889469641","https://openalex.org/W2904383797","https://openalex.org/W2912354537","https://openalex.org/W2940262938","https://openalex.org/W2943987826","https://openalex.org/W2955570969","https://openalex.org/W2962778872","https://openalex.org/W2962891704","https://openalex.org/W2963150697","https://openalex.org/W2963799213","https://openalex.org/W2964121744","https://openalex.org/W2965946035","https://openalex.org/W2969814989","https://openalex.org/W2979634944","https://openalex.org/W2981669902","https://openalex.org/W2990578762","https://openalex.org/W3089090082"],"related_works":["https://openalex.org/W4316660077","https://openalex.org/W4399204337","https://openalex.org/W3162018314","https://openalex.org/W3197006556","https://openalex.org/W4383748094","https://openalex.org/W4402979744","https://openalex.org/W4226159130","https://openalex.org/W2946824094","https://openalex.org/W4409473954","https://openalex.org/W6990792693"],"abstract_inverted_index":{"Segmentation":[0],"of":[1,8,13,18,28,125,140,181,239],"ultra-high":[2,86,115],"resolution":[3,80,87,116],"images":[4,25],"is":[5,146],"challenging":[6],"because":[7],"their":[9],"enormous":[10],"size,":[11],"consisting":[12],"millions":[14],"or":[15],"even":[16],"billions":[17],"pixels.":[19],"Typical":[20],"solutions":[21],"include":[22],"dividing":[23],"input":[24,127],"into":[26],"patches":[27,180],"fixed":[29,182],"size":[30],"and/or":[31],"down-sampling":[32],"to":[33,96,129,131,153],"meet":[34],"memory":[35],"constraints.":[36],"Such":[37],"operations":[38],"incur":[39],"information":[40],"loss":[41],"in":[42,100,226],"the":[43,50,75,82,97,120,126,132,141,150,155,168,176,188,192,198,209,223,227,236],"field-of-view":[44],"(FoV)":[45],"i.e.,":[46],"spatial":[47,138],"coverage":[48],"and":[49,79,214,220,231,233,245,249],"image":[51,165,195],"resolution.":[52],"The":[53,143],"impact":[54],"on":[55,85,160,191,235],"segmentation":[56,83,134,151,173,206],"performance":[57,84,174,190,238],"is,":[58],"however,":[59],"as":[60],"yet":[61],"understudied.":[62],"In":[63],"this":[64],"work,":[65],"we":[66],"start":[67],"with":[68,149,179],"a":[69,108,113],"motivational":[70],"experiment":[71],"which":[72],"demonstrates":[73],"that":[74,167],"trade-off":[76],"between":[77],"FoV":[78],"affects":[81],"images---and":[88],"furthermore,":[89],"its":[90],"influence":[91],"also":[92],"varies":[93],"spatially":[94],"according":[95],"local":[98],"patterns":[99],"different":[101],"areas.":[102],"We":[103,158],"then":[104],"introduce":[105],"foveation":[106,144,169],"module,":[107],"learnable":[109],"\"dataloader\"":[110],"which,":[111],"for":[112,208],"given":[114],"image,":[117],"adaptively":[118],"chooses":[119],"appropriate":[121],"configuration":[122],"(FoV/resolution":[123],"trade-off)":[124],"patch":[128],"feed":[130],"downstream":[133],"model":[135,203],"at":[136,254],"each":[137],"location":[139],"image.":[142],"module":[145,170],"jointly":[147],"trained":[148,178,250],"network":[152],"maximise":[154],"task":[156],"performance.":[157],"demonstrate":[159],"three":[161],"publicly":[162],"available":[163,253],"high-resolution":[164],"datasets":[166],"consistently":[171],"improves":[172,234],"over":[175],"cases":[177],"FoV/resolution":[183],"trade-off.":[184],"Our":[185,247],"approach":[186],"achieves":[187,204],"SoTA":[189],"DeepGlobe":[193],"aerial":[194],"dataset.":[196],"On":[197],"Gleason2019":[199],"histopathology":[200],"dataset,":[201],"our":[202],"better":[205],"accuracy":[207],"two":[210],"most":[211],"clinically":[212],"important":[213],"ambiguous":[215],"classes":[216],"(Gleason":[217],"Grade":[218],"3":[219],"4)":[221],"than":[222],"top":[224],"performers":[225],"challenge":[228],"by":[229,243],"13.1%":[230],"7.5%,":[232],"average":[237],"6":[240],"human":[241],"experts":[242],"6.5%":[244],"7.5%.":[246],"code":[248],"models":[251],"are":[252],"$\\text{https://github.com/lxasqjc/Foveation-Segmentation}$.":[255]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2020-08-03T00:00:00"}