{"id":"https://openalex.org/W7214923944","doi":"https://doi.org/10.48550/arxiv.2609.37638","title":"Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model","display_name":"Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214923944","doi":"https://doi.org/10.48550/arxiv.2609.37638"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.37638","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37638","pdf_url":"https://arxiv.org/pdf/2609.37638","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/2609.37638","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103220519","display_name":"Van Bach Nguyen","orcid":"https://orcid.org/0000-0002-4576-9302","observed_orcids":["https://orcid.org/0000-0002-4576-9302"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Van Bach","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029341868","display_name":"J\u00f6rg Schl\u00f6tterer","orcid":"https://orcid.org/0000-0002-3678-0390","observed_orcids":["https://orcid.org/0000-0002-3678-0390"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schl\u00f6tterer, J\u00f6rg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5153684357","display_name":"Christin Seifer","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seifer, Christin","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":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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9994999766349792,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9994999766349792,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.00019999999494757503,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.00019999999494757503,"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/counterfactual-explanations","display_name":"counterfactual explanations","score":0.9179999828338623},{"id":"https://openalex.org/keywords/clip","display_name":"CLIP","score":0.9959999918937683},{"id":"https://openalex.org/keywords/zero-shot-classification","display_name":"zero-shot classification","score":0.8100000023841858},{"id":"https://openalex.org/keywords/image-editing","display_name":"image editing","score":0.5730000138282776},{"id":"https://openalex.org/keywords/photorealism","display_name":"photorealism","score":0.4339999854564667},{"id":"https://openalex.org/keywords/explainable-ai","display_name":"explainable AI","score":0.6140000224113464}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.92330002784729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6272000074386597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.552299976348877},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.5216000080108643},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4781000018119812},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.44530001282691956},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.4447000026702881},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36410000920295715},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33079999685287476},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.32199999690055847},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.31949999928474426},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2816999852657318},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27790001034736633},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C543847140","wikidata":"https://www.wikidata.org/wiki/Q2642826","display_name":"Realism","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.2522999942302704},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.37638","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37638","pdf_url":"https://arxiv.org/pdf/2609.37638","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.2609.37638","doi":"https://doi.org/10.48550/arxiv.2609.37638","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.37638","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.37638","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37638","pdf_url":"https://arxiv.org/pdf/2609.37638","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4388726935","https://openalex.org/W4409261929","https://openalex.org/W4407056550","https://openalex.org/W4304091651","https://openalex.org/W7171514705","https://openalex.org/W7202206731","https://openalex.org/W4401157522","https://openalex.org/W4297847105","https://openalex.org/W7203669505","https://openalex.org/W7222914569"],"abstract_inverted_index":{"Current":[0],"explanation":[1],"methods":[2],"for":[3,42],"contrastive":[4],"vision-language":[5],"models":[6],"such":[7],"as":[8],"CLIP":[9,43,85,166],"mainly":[10],"identify":[11],"important":[12],"regions":[13],"without":[14],"showing":[15],"how":[16],"to":[17,23,66,96],"change":[18],"the":[19,61,79,92,97,114,125,129,137,153],"input":[20],"in":[21],"order":[22],"get":[24],"a":[25,35,68,83,148,171],"target":[26,70,116],"prediction.":[27],"We":[28,100],"introduce":[29],"Mask-guided":[30],"Adaptive":[31],"Counterfactual":[32],"Explanations":[33],"(MACE),":[34],"targeted":[36],"visual":[37],"counterfactual":[38,174],"method":[39],"designed":[40],"specifically":[41],"zero-shot":[44],"classification.":[45],"MACE":[46,102],"constructs":[47],"an":[48],"editable":[49],"region":[50],"from":[51],"either":[52],"source":[53],"attribution":[54,57],"or":[55],"source-target":[56],"differences":[58],"and":[59,90,108,133,136,145,176],"expands":[60],"mask":[62],"only":[63],"when":[64],"needed":[65],"reach":[67],"specified":[69],"class.":[71],"A":[72],"latent":[73],"diffusion":[74],"inpainting":[75],"model":[76,86],"then":[77],"modifies":[78],"selected":[80],"region,":[81],"while":[82,124],"frozen":[84],"provides":[87],"modification":[88],"guidance":[89],"anchors":[91],"remaining":[93],"image":[94],"content":[95],"original":[98],"input.":[99],"evaluate":[101],"on":[103],"ImageNet,":[104],"Food-101,":[105],"Oxford":[106],"Pets,":[107],"CUB-200.":[109],"The":[110],"source-mask":[111],"variant":[112,127],"achieves":[113],"highest":[115],"top-1":[117],"success":[118],"rate":[119],"across":[120],"all":[121],"four":[122],"datasets,":[123],"difference-mask":[126],"produces":[128,164],"smallest":[130],"pixel":[131],"level":[132],"perceptual":[134],"changes":[135],"best":[138],"realism":[139,146],"scores.":[140],"Both":[141],"variants":[142],"improve":[143],"proximity":[144],"over":[147],"Stable":[149],"Diffusion-only":[150],"baseline":[151],"using":[152],"same":[154],"generative":[155],"backbone.":[156],"These":[157],"results":[158],"show":[159],"that":[160],"adaptive":[161],"mask-guided":[162],"editing":[163],"effective":[165],"counterfactuals.":[167],"They":[168],"further":[169],"reveal":[170],"tradeoff":[172],"between":[173],"validity":[175],"source-image":[177],"preservation.":[178]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-01T00:00:00"}