{"id":"https://openalex.org/W4410609251","doi":"https://doi.org/10.1109/satml64287.2025.00042","title":"Err on the Side of Texture: Texture Bias on Real Data","display_name":"Err on the Side of Texture: Texture Bias on Real Data","publication_year":2025,"publication_date":"2025-04-09","ids":{"openalex":"https://openalex.org/W4410609251","doi":"https://doi.org/10.1109/satml64287.2025.00042"},"language":"en","primary_location":{"id":"doi:10.1109/satml64287.2025.00042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/satml64287.2025.00042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088915686","display_name":"Blaine Hoak","orcid":"https://orcid.org/0000-0003-2960-0686"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Blaine Hoak","raw_affiliation_strings":["University of Wisconsin-Madison,Department of Computer Sciences,USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison,Department of Computer Sciences,USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056794879","display_name":"Ryan Sheatsley","orcid":"https://orcid.org/0000-0001-8447-602X"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryan Sheatsley","raw_affiliation_strings":["University of Wisconsin-Madison,Department of Computer Sciences,USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison,Department of Computer Sciences,USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055368149","display_name":"Patrick McDaniel","orcid":"https://orcid.org/0000-0003-2091-7484"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick McDaniel","raw_affiliation_strings":["University of Wisconsin-Madison,Department of Computer Sciences,USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison,Department of Computer Sciences,USA","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088915686"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":2.8582,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9010008,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"661","last_page":"680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.3596000075340271,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.3596000075340271,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/texture","display_name":"Texture (cosmology)","score":0.7277383804321289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6056520938873291},{"id":"https://openalex.org/keywords/image-texture","display_name":"Image texture","score":0.4876329004764557},{"id":"https://openalex.org/keywords/texture-filtering","display_name":"Texture filtering","score":0.45177358388900757},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4416273832321167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42584237456321716},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10224491357803345},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.096434086561203}],"concepts":[{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.7277383804321289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6056520938873291},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.4876329004764557},{"id":"https://openalex.org/C144743038","wikidata":"https://www.wikidata.org/wiki/Q3267765","display_name":"Texture filtering","level":5,"score":0.45177358388900757},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4416273832321167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42584237456321716},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10224491357803345},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.096434086561203}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/satml64287.2025.00042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/satml64287.2025.00042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6290504362","display_name":null,"funder_award_id":"CNS2343611","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2047643928","https://openalex.org/W2099001231","https://openalex.org/W2117539524","https://openalex.org/W2243397390","https://openalex.org/W2475287302","https://openalex.org/W2543927648","https://openalex.org/W2800564132","https://openalex.org/W2963749936","https://openalex.org/W2963857521","https://openalex.org/W3011711787","https://openalex.org/W3016970897","https://openalex.org/W3034001813","https://openalex.org/W3103836116","https://openalex.org/W3138049982","https://openalex.org/W3177096435","https://openalex.org/W4312443924","https://openalex.org/W4390872430","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6683590716","https://openalex.org/W6685736903","https://openalex.org/W6686164453","https://openalex.org/W6687483927","https://openalex.org/W6715285673","https://openalex.org/W6725739302","https://openalex.org/W6729756640","https://openalex.org/W6739868092","https://openalex.org/W6753695549","https://openalex.org/W6756444276","https://openalex.org/W6757555829","https://openalex.org/W6758132781","https://openalex.org/W6762718338","https://openalex.org/W6763111939","https://openalex.org/W6780851395","https://openalex.org/W6784515117","https://openalex.org/W6843590153","https://openalex.org/W6862126205"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W1980033651","https://openalex.org/W4230530180","https://openalex.org/W2044270176","https://openalex.org/W2388733570","https://openalex.org/W2374828682","https://openalex.org/W2153116791"],"abstract_inverted_index":{"Bias":[0],"significantly":[1],"undermines":[2],"both":[3],"the":[4,16,65,80,109,127],"accuracy":[5,94],"and":[6,42,95],"trustworthiness":[7],"of":[8,15,82,111,118,130],"machine":[9],"learning":[10],"models.":[11],"To":[12],"date,":[13],"one":[14],"strongest":[17],"biases":[18],"observed":[19],"in":[20,57,135],"image":[21],"classification":[22],"models":[23,27,77],"is":[24],"texture":[25,31,44,106,129],"bias-where":[26],"overly":[28],"rely":[29,78],"on":[30,79],"information":[32],"rather":[33],"than":[34],"shape":[35],"information.":[36],"Yet,":[37],"existing":[38],"approaches":[39],"for":[40],"measuring":[41],"mitigating":[43],"bias":[45,107],"have":[46],"not":[47],"been":[48],"able":[49],"to":[50],"capture":[51],"how":[52,75],"textures":[53,84,122],"impact":[54],"model":[55,93],"robustness":[56,96],"real-world":[58],"settings.":[59],"In":[60],"this":[61],"work,":[62],"we":[63,90],"introduce":[64],"Texture":[66],"Association":[67],"Value":[68],"(TAV),":[69],"a":[70],"novel":[71],"metric":[72],"that":[73,92,105,123],"quantifies":[74],"strongly":[76],"presence":[81],"specific":[83],"when":[85],"classifying":[86],"objects.":[87],"Leveraging":[88],"TAV,":[89],"demonstrate":[91],"are":[97,124],"heavily":[98],"influenced":[99],"by":[100],"texture.":[101],"Our":[102],"results":[103],"show":[104],"explains":[108],"existence":[110],"natural":[112],"adversarial":[113],"examples,":[114],"where":[115],"over":[116],"90%":[117],"these":[119],"samples":[120],"contain":[121],"misaligned":[125],"with":[126],"learned":[128],"their":[131],"true":[132],"label,":[133],"resulting":[134],"confident":[136],"mispredictions.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}