{"id":"https://openalex.org/W4221145040","doi":"https://doi.org/10.48550/arxiv.2203.09343","title":"CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in Segmentation","display_name":"CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in Segmentation","publication_year":2022,"publication_date":"2022-03-17","ids":{"openalex":"https://openalex.org/W4221145040","doi":"https://doi.org/10.48550/arxiv.2203.09343"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2203.09343","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.09343","pdf_url":"https://arxiv.org/pdf/2203.09343","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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.09343","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069288224","display_name":"Renhao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Renhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418988","display_name":"Hang Zhao","orcid":"https://orcid.org/0009-0008-7252-3827"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Hang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100324800","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0003-0051-9120"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Yang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069288224"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.998199999332428,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.998199999332428,"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":0.9969000220298767,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9966999888420105,"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":0.8063585758209229},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7292391061782837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6952499747276306},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5839335918426514},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5760419964790344},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.48400065302848816},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4544019401073456},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4247414469718933},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.4221112132072449},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4148053228855133},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3948880434036255},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3714540898799896},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10015228390693665}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8063585758209229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7292391061782837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6952499747276306},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5839335918426514},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5760419964790344},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.48400065302848816},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4544019401073456},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4247414469718933},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.4221112132072449},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4148053228855133},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3948880434036255},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3714540898799896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10015228390693665},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2203.09343","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.09343","pdf_url":"https://arxiv.org/pdf/2203.09343","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2203.09343","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.09343","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.09343","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.09343","pdf_url":"https://arxiv.org/pdf/2203.09343","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1534274833","https://openalex.org/W3117246195","https://openalex.org/W156620619","https://openalex.org/W2616249226","https://openalex.org/W2098233217","https://openalex.org/W2914363205","https://openalex.org/W1598221548","https://openalex.org/W2081850291","https://openalex.org/W1963695443","https://openalex.org/W2997844990"],"abstract_inverted_index":{"Many":[0],"recent":[1],"approaches":[2],"in":[3,40,118,136],"contrastive":[4,95,116],"learning":[5,79],"have":[6],"worked":[7],"to":[8,52,88,103,133],"close":[9],"the":[10,99,115],"gap":[11,27],"between":[12,109],"pretraining":[13,20],"on":[14,21],"iconic":[15],"images":[16,43],"like":[17,24],"ImageNet":[18],"and":[19,82,97,121,139],"complex":[22],"scenes":[23],"COCO.":[25],"This":[26],"exists":[28],"largely":[29],"because":[30],"commonly":[31],"used":[32],"random":[33],"crop":[34],"augmentations":[35],"obtain":[36],"semantically":[37],"inconsistent":[38],"content":[39],"crowded":[41],"scene":[42],"of":[44,80],"diverse":[45],"objects.":[46],"Previous":[47],"works":[48],"use":[49,98],"preprocessing":[50],"pipelines":[51],"localize":[53],"salient":[54],"objects":[55],"for":[56],"improved":[57],"cropping,":[58],"but":[59],"an":[60],"end-to-end":[61],"solution":[62],"is":[63],"still":[64],"elusive.":[65],"In":[66],"this":[67,75],"work,":[68],"we":[69,113],"propose":[70],"a":[71,90,93],"framework":[72],"which":[73],"accomplishes":[74],"goal":[76],"via":[77],"joint":[78],"representations":[81,130],"segmentation.":[83,140],"We":[84],"leverage":[85],"segmentation":[86,119,124],"masks":[87],"train":[89],"model":[91,102],"with":[92],"mask-dependent":[94],"loss,":[96],"partially":[100],"trained":[101],"bootstrap":[104],"better":[105],"masks.":[106],"By":[107],"iterating":[108],"these":[110],"two":[111],"components,":[112],"ground":[114],"updates":[117],"information,":[120],"simultaneously":[122],"improve":[123],"throughout":[125],"pretraining.":[126],"Experiments":[127],"show":[128],"our":[129],"transfer":[131],"robustly":[132],"downstream":[134],"tasks":[135],"classification,":[137],"detection":[138]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}