{"id":"https://openalex.org/W4415199642","doi":"https://doi.org/10.1109/iccv51701.2025.02050","title":"Modeling Saliency Dataset Bias","display_name":"Modeling Saliency Dataset Bias","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415199642","doi":"https://doi.org/10.1109/iccv51701.2025.02050"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.10169","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068221391","display_name":"Matthias K\u00fcmmerer","orcid":"https://orcid.org/0000-0001-9644-4703"},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias K\u00fcmmerer","raw_affiliation_strings":["University of Tübingen,Tübingen AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tübingen,Tübingen AI Center","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048529667","display_name":"Harneet Singh Khanuja","orcid":null},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Harneet Singh Khanuja","raw_affiliation_strings":["University of Tübingen,Tübingen AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tübingen,Tübingen AI Center","institution_ids":["https://openalex.org/I143910747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061457780","display_name":"Matthias Bethge","orcid":"https://orcid.org/0000-0002-6417-7812"},"institutions":[{"id":"https://openalex.org/I143910747","display_name":"TH Bingen University of Applied Sciences","ror":"https://ror.org/01pxkj057","country_code":"DE","type":"education","lineage":["https://openalex.org/I143910747"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matthias Bethge","raw_affiliation_strings":["University of Tübingen,Tübingen AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tübingen,Tübingen AI Center","institution_ids":["https://openalex.org/I143910747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143910747"],"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":"22077","last_page":"22088"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.6891000270843506,"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":0.6891000270843506,"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/generalization","display_name":"Generalization","score":0.6008999943733215},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5954999923706055},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4715999960899353},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4480000138282776},{"id":"https://openalex.org/keywords/fraction","display_name":"Fraction (chemistry)","score":0.3407999873161316},{"id":"https://openalex.org/keywords/saliency-map","display_name":"Saliency map","score":0.3393000066280365}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6877999901771545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769999861717224},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6008999943733215},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5954999923706055},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5134999752044678},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4715999960899353},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4480000138282776},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C2779679900","wikidata":"https://www.wikidata.org/wiki/Q25304431","display_name":"Saliency map","level":3,"score":0.3393000066280365},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3109000027179718},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2766000032424927},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C188154048","wikidata":"https://www.wikidata.org/wiki/Q6803609","display_name":"Mean absolute error","level":3,"score":0.26829999685287476}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.10169","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.10169","pdf_url":"https://arxiv.org/pdf/2505.10169","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"},{"id":"doi:10.48550/arxiv.2505.10169","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.10169","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.10169","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.10169","pdf_url":"https://arxiv.org/pdf/2505.10169","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/G4262206430","display_name":null,"funder_award_id":"SFB 1233","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4415199642.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"image-based":[3],"saliency":[4,25,181],"prediction":[5],"are":[6,47],"approaching":[7],"gold":[8],"standard":[9],"performance":[10,37],"levels":[11],"on":[12,44,141],"existing":[13],"benchmarks.":[14],"Despite":[15],"this":[16,58,71],"success,":[17],"we":[18,75],"show":[19],"that":[20,92,187],"predicting":[21],"fixations":[22],"across":[23],"multiple":[24],"datasets":[26,144],"remains":[27],"challenging":[28],"due":[29],"to":[30,49,63,66,109,168],"dataset":[31,46,53],"bias.":[32],"We":[33],"find":[34],"a":[35,77,81,122,138,163],"significant":[36],"drop":[38],"(around":[39],"40%)":[40],"when":[41,155,166],"models":[42],"trained":[43],"one":[45],"applied":[48],"another.":[50],"Surprisingly,":[51],"increasing":[52],"diversity":[54],"does":[55],"not":[56],"resolve":[57],"inter-dataset":[59],"gap,":[60,74,120],"with":[61,86,121,129,162],"close":[62],"60%":[64],"attributed":[65],"dataset-specific":[67,90],"biases.":[68],"To":[69],"address":[70],"remaining":[72],"generalization":[73,119],"propose":[76],"novel":[78],"architecture":[79],"extending":[80],"mostly":[82],"dataset-agnostic":[83],"encoder-decoder":[84],"structure":[85],"fewer":[87],"than":[88,115],"20":[89],"parameters":[91,108],"govern":[93],"interpretable":[94],"mechanisms":[95],"such":[96],"as":[97,130,132],"multi-scale":[98,185],"structure,":[99],"center":[100],"bias,":[101],"and":[102,152,191],"fixation":[103],"spread.":[104],"Adapting":[105],"only":[106],"these":[107],"new":[110,139],"data":[111],"accounts":[112],"for":[113],"more":[114],"75%":[116],"of":[117,125,145],"the":[118,126,146,169],"large":[123],"fraction":[124],"improvement":[127],"achieved":[128],"few":[131],"50":[133],"samples.":[134],"Our":[135],"model":[136,174],"sets":[137],"state-of-the-art":[140],"all":[142],"three":[143],"MIT/Tuebingen":[147],"Saliency":[148],"Benchmark":[149],"(MIT300,":[150],"CAT2000,":[151],"COCO-Freeview),":[153],"even":[154],"purely":[156],"generalizing":[157],"from":[158],"unrelated":[159],"datasets,":[160],"but":[161],"substantial":[164],"boost":[165],"adapting":[167],"respective":[170],"training":[171],"datasets.":[172],"The":[173],"also":[175],"provides":[176],"valuable":[177],"insights":[178],"into":[179],"spatial":[180],"properties,":[182],"revealing":[183],"complex":[184],"effects":[186],"combine":[188],"both":[189],"absolute":[190],"relative":[192],"sizes.":[193]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-15T00:00:00"}