{"id":"https://openalex.org/W3137509541","doi":"https://doi.org/10.1145/3450439.3451865","title":"iGOS++","display_name":"iGOS++","publication_year":2021,"publication_date":"2021-03-23","ids":{"openalex":"https://openalex.org/W3137509541","doi":"https://doi.org/10.1145/3450439.3451865","mag":"3137509541"},"language":"en","primary_location":{"id":"doi:10.1145/3450439.3451865","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3450439.3451865","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3450439.3451865","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on Health, Inference, and Learning","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3450439.3451865","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103005789","display_name":"Saeed Khorram","orcid":"https://orcid.org/0000-0001-7027-0119"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Saeed Khorram","raw_affiliation_strings":["Oregon State University"],"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112618825","display_name":"Tyler Lawson","orcid":null},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tyler Lawson","raw_affiliation_strings":["Oregon State University"],"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065084526","display_name":"Fuxin Li","orcid":"https://orcid.org/0000-0001-7578-9622"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Fuxin","raw_affiliation_strings":["Oregon State University"],"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103005789"],"corresponding_institution_ids":["https://openalex.org/I131249849"],"apc_list":null,"apc_paid":null,"fwci":1.8195,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.87536804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"174","last_page":"182"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9958999752998352,"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":0.9919999837875366,"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/computer-science","display_name":"Computer science","score":0.8410559892654419},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7263321876525879},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7261824011802673},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7162572145462036},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.537310004234314},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48914864659309387},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.48809492588043213},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4619593620300293},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39839547872543335},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2616742253303528}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8410559892654419},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7263321876525879},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7261824011802673},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7162572145462036},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.537310004234314},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48914864659309387},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.48809492588043213},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4619593620300293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39839547872543335},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2616742253303528},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3450439.3451865","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3450439.3451865","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3450439.3451865","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on Health, Inference, and Learning","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3450439.3451865","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3450439.3451865","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3450439.3451865","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on Health, Inference, and Learning","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8680787740","display_name":null,"funder_award_id":"N66001-17-2-4030","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3137509541.pdf","grobid_xml":"https://content.openalex.org/works/W3137509541.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1787224781","https://openalex.org/W1849277567","https://openalex.org/W1899185266","https://openalex.org/W2012875423","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2282821441","https://openalex.org/W2295107390","https://openalex.org/W2503388974","https://openalex.org/W2560835477","https://openalex.org/W2606462007","https://openalex.org/W2774644650","https://openalex.org/W2891612330","https://openalex.org/W2943425778","https://openalex.org/W2949197630","https://openalex.org/W2962835968","https://openalex.org/W2962851944","https://openalex.org/W2962858109","https://openalex.org/W2963382180","https://openalex.org/W2963715038","https://openalex.org/W2964153729","https://openalex.org/W2967615747","https://openalex.org/W2988157455","https://openalex.org/W3101609372","https://openalex.org/W3106510235","https://openalex.org/W4245551996"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W3099765033"],"abstract_inverted_index":{"The":[0],"black-box":[1],"nature":[2],"of":[3,22,34,56,101,118,135,167,175,182,234],"the":[4,8,23,35,49,54,57,65,78,106,112,116,119,133,165,180,196,201,206,216,219,230,235],"deep":[5],"networks":[6,94],"makes":[7],"explanation":[9,27],"for":[10,38,45,59,92],"\"why\"":[11],"they":[12],"make":[13],"certain":[14],"predictions":[15],"extremely":[16],"challenging.":[17],"Saliency":[18],"maps":[19,41,91],"are":[20,157],"one":[21],"most":[24],"widely-used":[25],"local":[26],"tools":[28],"to":[29,88,111,200],"alleviate":[30],"this":[31,81,222],"problem.":[32],"One":[33],"primary":[36],"approaches":[37],"generating":[39],"saliency":[40,90,120,144],"is":[42,63,198],"by":[43,74,95,137,160,225],"optimizing":[44],"a":[46,60,86,172],"mask":[47],"over":[48],"input":[50],"dimensions":[51],"so":[52],"that":[53,114,156,194],"output":[55],"network":[58],"given":[61],"class":[62],"influenced":[64],"most.":[66],"However,":[67],"prior":[68],"work":[69],"only":[70],"studies":[71],"such":[72],"influence":[73],"removing":[75],"evidence":[76,217],"from":[77,186],"input.":[79],"In":[80],"paper,":[82],"we":[83,104,163,192],"present":[84],"iGOS++,":[85,170],"framework":[87],"generate":[89],"blackbox":[93],"considering":[96],"both":[97],"removal":[98],"and":[99,126,140,232],"preservation":[100],"evidence.":[102],"Additionally,":[103],"introduce":[105],"bilateral":[107],"total":[108],"variation":[109],"term":[110],"optimization":[113],"improves":[115],"continuity":[117],"map":[121,145],"especially":[122],"under":[123],"high":[124],"resolution":[125],"with":[127],"thin":[128],"object":[129],"parts.":[130],"We":[131],"validate":[132],"capabilities":[134,166],"iGOS++":[136],"extensive":[138],"experiments":[139],"comparison":[141],"against":[142],"state-of-the-art":[143],"methods.":[146],"Our":[147],"results":[148],"show":[149],"significant":[150],"improvement":[151],"in":[152,171,218],"locating":[153],"salient":[154],"regions":[155],"directly":[158],"interpretable":[159],"humans.":[161],"Besides,":[162],"showcased":[164],"our":[168,190],"method,":[169],"real-world":[173],"application":[174],"AI":[176],"on":[177,205,215],"medical":[178],"data:":[179],"task":[181],"classifying":[183],"COVID-19":[184],"cases":[185],"x-ray":[187,207],"images.":[188],"To":[189],"surprise,":[191],"discovered":[193],"sometimes":[195],"classifier":[197],"overfitted":[199],"text":[202],"characters":[203],"printed":[204],"images":[208],"when":[209],"performing":[210],"classification":[211],"rather":[212],"than":[213],"focusing":[214],"lungs.":[220],"Fixing":[221],"overfitting":[223],"issue":[224],"data":[226],"cleansing":[227],"significantly":[228],"improved":[229],"precision":[231],"recall":[233],"classifier.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2021-03-29T00:00:00"}