{"id":"https://openalex.org/W4416084100","doi":null,"title":"Enhancing Abnormality Grounding for Vision Language Models with Knowledge Descriptions","display_name":"Enhancing Abnormality Grounding for Vision Language Models with Knowledge Descriptions","publication_year":2025,"publication_date":"2025-03-05","ids":{"openalex":"https://openalex.org/W4416084100"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.03278","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.03278","pdf_url":"https://arxiv.org/pdf/2503.03278","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","is_traditional":true,"indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.03278","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100362041","display_name":"Jun Li","orcid":"https://orcid.org/0000-0003-1613-9448","observed_orcids":["https://orcid.org/0000-0003-1613-9448","https://orcid.org/0000-0002-9781-8954","https://orcid.org/0009-0009-9854-9694","https://orcid.org/0000-0003-1693-0264"]},"institutions":[{"id":"https://openalex.org/I4403386549","display_name":"Munich Center for Machine Learning","ror":"https://ror.org/02nfy3535","country_code":"DE","type":"education","lineage":["https://openalex.org/I4403386549","https://openalex.org/I62916508","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Li, Jun","raw_affiliation_strings":["Munich Center for Machine Learning , Germany","Technical University of Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Munich Center for Machine Learning , Germany","institution_ids":["https://openalex.org/I4403386549"]},{"raw_affiliation_string":"Technical University of Munich , Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103477299","display_name":"Che Liu","orcid":"https://orcid.org/0009-0004-3738-7998","observed_orcids":["https://orcid.org/0009-0004-3738-7998"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Che","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059823739","display_name":"Wenjia Bai","orcid":"https://orcid.org/0000-0003-2943-7698","observed_orcids":["https://orcid.org/0000-0003-2943-7698"]},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bai, Wenjia","raw_affiliation_strings":["Imperial College London , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London , UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085852399","display_name":"Rossella Arcucci","orcid":"https://orcid.org/0000-0002-9471-0585","observed_orcids":["https://orcid.org/0000-0002-9471-0585"]},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arcucci, Rossella","raw_affiliation_strings":["Imperial College London , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London , UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086799838","display_name":"Cosmin I. Bercea","orcid":"https://orcid.org/0000-0003-2628-2766","observed_orcids":["https://orcid.org/0000-0003-2628-2766"]},"institutions":[{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Munich","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bercea, Cosmin I.","raw_affiliation_strings":["Helmholtz AI and Helmholtz Munich , Germany","Technical University of Munich , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Helmholtz AI and Helmholtz Munich , Germany","institution_ids":["https://openalex.org/I3018134672"]},{"raw_affiliation_string":"Technical University of Munich , Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019012882","display_name":"Julia A. Schnabel","orcid":"https://orcid.org/0000-0001-6107-3009","observed_orcids":["https://orcid.org/0000-0001-6107-3009","https://orcid.org/0000-0001-6755-8672"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schnabel, Julia A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976000189781189,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976000189781189,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.0005000000237487257,"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/visual-grounding","display_name":"visual grounding","score":0.8090000152587891},{"id":"https://openalex.org/keywords/anomaly-localization","display_name":"anomaly localization","score":0.9129999876022339},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8149999976158142},{"id":"https://openalex.org/keywords/medical-terminology","display_name":"medical terminology","score":0.5490000247955322},{"id":"https://openalex.org/keywords/florence-2","display_name":"Florence-2","score":0.6830000281333923},{"id":"https://openalex.org/keywords/llava","display_name":"LLaVA","score":0.9819999933242798}],"concepts":[{"id":"https://openalex.org/C50965678","wikidata":"https://www.wikidata.org/wiki/Q2724302","display_name":"Abnormality","level":2,"score":0.8600999712944031},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6829000115394592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6281999945640564},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6105999946594238},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5327000021934509},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4381999969482422},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36959999799728394},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C2985722590","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medical knowledge","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3093999922275543},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C2983864324","wikidata":"https://www.wikidata.org/wiki/Q16872183","display_name":"Line drawings","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2503.03278","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.03278","pdf_url":"https://arxiv.org/pdf/2503.03278","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":"pmh:oai:kclpure.kcl.ac.uk:publications/8f788214-51c2-4979-bee9-a6a1f58b3bce","doi":null,"is_oa":true,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/8f788214-51c2-4979-bee9-a6a1f58b3bce","pdf_url":"https://kclpure.kcl.ac.uk/portal/files/327229471/2503.03278v1.pdf","source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Li, J, Liu, C, Bai, W, Arcucci, R, Bercea, C I & Schnabel, J A 2025 'Enhancing Abnormality Grounding for Vision Language Models with Knowledge Descriptions'.","raw_type":"info:eu-repo/semantics/preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.03278","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.03278","pdf_url":"https://arxiv.org/pdf/2503.03278","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416084100.pdf","grobid_xml":"https://content.openalex.org/works/W4416084100.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W3209525070","https://openalex.org/W4327810158","https://openalex.org/W4377121462","https://openalex.org/W4386185600","https://openalex.org/W4391159111","https://openalex.org/W4392678661","https://openalex.org/W4394659038","https://openalex.org/W4399251815","https://openalex.org/W4399510493","https://openalex.org/W4400680052","https://openalex.org/W4404389169","https://openalex.org/W4407231314","https://openalex.org/W4416011362"],"related_works":["https://openalex.org/W7160296877","https://openalex.org/W4412945210","https://openalex.org/W4415934781","https://openalex.org/W4403581960","https://openalex.org/W7138460110","https://openalex.org/W7146997525","https://openalex.org/W4408011351","https://openalex.org/W4414380972","https://openalex.org/W4415328512","https://openalex.org/W7170721918"],"abstract_inverted_index":{"Visual":[0],"Language":[1],"Models":[2],"(VLMs)":[3],"have":[4],"demonstrated":[5],"impressive":[6],"capabilities":[7],"in":[8,15,69,123,142,174],"visual":[9,55,101,113],"grounding":[10,144],"tasks.":[11],"However,":[12],"their":[13,53],"effectiveness":[14,170],"the":[16,34,117,130,159,169],"medical":[17,26,40,70,78,94,124,150],"domain,":[18],"particularly":[19],"for":[20,162],"abnormality":[21,71,143],"detection":[22,72],"and":[23,36,73,99,112,119,135,177],"localization":[24,74,120],"within":[25],"images,":[27],"remains":[28],"underexplored.":[29],"A":[30],"major":[31],"challenge":[32],"is":[33],"complex":[35],"abstract":[37],"nature":[38],"of":[39,81,121,158,171],"terminology,":[41],"which":[42],"makes":[43],"it":[44,138],"difficult":[45],"to":[46,65,85,145],"directly":[47,82],"associate":[48],"pathological":[49],"anomaly":[50],"terms":[51],"with":[52],"corresponding":[54],"features.":[56],"In":[57],"this":[58],"work,":[59],"we":[60,89],"introduce":[61],"a":[62,106],"novel":[63],"approach":[64,173],"enhance":[66],"VLM":[67],"performance":[68,141],"by":[75],"leveraging":[76],"decomposed":[77],"knowledge.":[79],"Instead":[80],"prompting":[83],"models":[84],"recognize":[86],"specific":[87],"abnormalities,":[88,180],"focus":[90],"on":[91,129,155],"breaking":[92],"down":[93],"concepts":[95],"into":[96],"fundamental":[97],"attributes":[98],"common":[100],"patterns.":[102],"This":[103],"strategy":[104],"promotes":[105],"stronger":[107],"alignment":[108],"between":[109],"textual":[110],"descriptions":[111],"features,":[114],"improving":[115],"both":[116,175],"recognition":[118],"abnormalities":[122],"images.We":[125],"evaluate":[126],"our":[127,172],"method":[128],"0.23B":[131],"Florence-2":[132],"base":[133],"model":[134],"demonstrate":[136,168],"that":[137],"achieves":[139],"comparable":[140],"significantly":[146],"larger":[147],"7B":[148],"LLaVA-based":[149],"VLMs,":[151],"despite":[152],"being":[153],"trained":[154],"only":[156],"1.5%":[157],"data":[160],"used":[161],"such":[163],"models.":[164],"Experimental":[165],"results":[166],"also":[167],"known":[176],"previously":[178],"unseen":[179],"suggesting":[181],"its":[182],"strong":[183],"generalization":[184],"capabilities.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}