{"id":"https://openalex.org/W2948252829","doi":"https://doi.org/10.1145/3299869.3319874","title":"Incremental and Approximate Inference for Faster Occlusion-based Deep CNN Explanations","display_name":"Incremental and Approximate Inference for Faster Occlusion-based Deep CNN Explanations","publication_year":2019,"publication_date":"2019-06-18","ids":{"openalex":"https://openalex.org/W2948252829","doi":"https://doi.org/10.1145/3299869.3319874","mag":"2948252829"},"language":"en","primary_location":{"id":"doi:10.1145/3299869.3319874","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3299869.3319874","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3299869.3319874","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","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/10.1145/3299869.3319874","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075059497","display_name":"Supun Nakandala","orcid":"https://orcid.org/0000-0002-2541-1944"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Supun Nakandala","raw_affiliation_strings":["University of California, San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103749365","display_name":"Arun Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arun Kumar","raw_affiliation_strings":["University of California, San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059167302","display_name":"Yannis Papakonstantinou","orcid":"https://orcid.org/0009-0007-6360-9496"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yannis Papakonstantinou","raw_affiliation_strings":["University of California, San Diego, La Jolla, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075059497"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":3.3237,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93879459,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1589","last_page":"1606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9980000257492065,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9927999973297119,"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":0.8426169753074646},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7720330357551575},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6638890504837036},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5744302272796631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5441104769706726},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4991724491119385},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.4690314531326294},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4677458107471466},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3872218132019043},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.348782479763031},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1855955421924591}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8426169753074646},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7720330357551575},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6638890504837036},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5744302272796631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5441104769706726},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4991724491119385},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.4690314531326294},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4677458107471466},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3872218132019043},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.348782479763031},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1855955421924591},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3299869.3319874","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3299869.3319874","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3299869.3319874","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3299869.3319874","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3299869.3319874","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3299869.3319874","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 International Conference on Management of Data","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G172287093","display_name":null,"funder_award_id":"R01DK114945","funder_id":"https://openalex.org/F4320337357","funder_display_name":"National Institute of Diabetes and Digestive and Kidney Diseases"},{"id":"https://openalex.org/G197008112","display_name":null,"funder_award_id":"NIDDK","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2190818908","display_name":null,"funder_award_id":"R01DK114945","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2642017051","display_name":null,"funder_award_id":"R01DK11","funder_id":"https://openalex.org/F4320337357","funder_display_name":"National Institute of Diabetes and Digestive and Kidney Diseases"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337357","display_name":"National Institute of Diabetes and Digestive and Kidney Diseases","ror":"https://ror.org/00adh9b73"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2948252829.pdf","grobid_xml":"https://content.openalex.org/works/W2948252829.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W187851124","https://openalex.org/W253264081","https://openalex.org/W1586825695","https://openalex.org/W1686810756","https://openalex.org/W1849277567","https://openalex.org/W1943411325","https://openalex.org/W1973761208","https://openalex.org/W1975733288","https://openalex.org/W2026102093","https://openalex.org/W2058978608","https://openalex.org/W2086140762","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2133665775","https://openalex.org/W2182763013","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2282821441","https://openalex.org/W2467799498","https://openalex.org/W2556967412","https://openalex.org/W2559655401","https://openalex.org/W2606822607","https://openalex.org/W2613621736","https://openalex.org/W2617049221","https://openalex.org/W2752236330","https://openalex.org/W2761434131","https://openalex.org/W2781265533","https://openalex.org/W2784477424","https://openalex.org/W2788633781","https://openalex.org/W2913201029","https://openalex.org/W2962851944","https://openalex.org/W2962858109","https://openalex.org/W2963363373","https://openalex.org/W2963387679","https://openalex.org/W2963893493","https://openalex.org/W3098547670","https://openalex.org/W4236965008"],"related_works":["https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3029198973","https://openalex.org/W4226287370","https://openalex.org/W2114556850","https://openalex.org/W2159992248","https://openalex.org/W2215785064"],"abstract_inverted_index":{"Deep":[0],"Convolutional":[1],"Neural":[2],"Networks":[3],"(CNNs)":[4],"now":[5],"match":[6],"human":[7],"accuracy":[8],"in":[9,15,19,179],"many":[10,34],"image":[11,58,70],"prediction":[12,87],"tasks,":[13],"resulting":[14],"a":[16,30,62,66,72,80,121,133,183],"growing":[17],"adoption":[18],"e-commerce,":[20],"radiology,":[21],"and":[22,74,107,135,167,192,198],"other":[23],"domains.":[24],"Naturally,":[25],"explaining":[26],"CNN":[27,141],"predictions":[28],"is":[29,92],"key":[31],"concern":[32],"for":[33,44,52,61,139],"users.":[35],"Since":[36],"the":[37,69,86,97,117,125,163,168],"internal":[38],"workings":[39],"of":[40,56,68,83,100,124,165],"CNNs":[41,166,199],"are":[42,50],"unintuitive":[43],"most":[45,60],"users,":[46],"occlusion-based":[47],"explanations":[48],"(OBE)":[49],"popular":[51],"understanding":[53],"which":[54,104],"parts":[55],"an":[57],"matter":[59],"prediction.":[63],"One":[64],"occludes":[65],"region":[67],"using":[71],"patch":[73],"moves":[75],"it":[76],"around":[77],"to":[78,85,96,149,171,181,207,211],"produce":[79,212],"heat":[81],"map":[82],"changes":[84],"probability.":[88],"Alas,":[89],"this":[90,113],"approach":[91],"computationally":[93],"expensive":[94],"due":[95],"large":[98],"number":[99],"re-inference":[101],"requests":[102],"produced,":[103],"wastes":[105],"time":[106],"raises":[108],"resource":[109,220],"costs.":[110,152],"We":[111,131,153,175],"tackle":[112],"issue":[114],"by":[115,205],"casting":[116],"OBE":[118,169],"task":[119,170],"as":[120],"new":[122],"instance":[123],"classical":[126],"incremental":[127,140],"view":[128],"maintenance":[129],"problem.":[130],"create":[132,182],"novel":[134,157],"comprehensive":[136],"algebraic":[137],"framework":[138],"inference":[142,159],"combining":[143],"materialized":[144],"views":[145],"with":[146,195],"multi-query":[147],"optimization":[148],"reduce":[150,173],"computational":[151],"then":[154],"present":[155],"two":[156],"approximate":[158],"optimizations":[160],"that":[161,188,201],"exploit":[162],"semantics":[164],"further":[172],"runtimes.":[174],"prototype":[176],"our":[177],"ideas":[178],"Python":[180],"tool":[184],"we":[185],"call":[186],"Krypton":[187,202],"supports":[189],"both":[190],"CPUs":[191],"GPUs.":[193],"Experiments":[194],"real":[196],"data":[197],"show":[200],"reduces":[203],"runtimes":[204],"up":[206],"5X":[208],"(resp.":[209,214],"35X)":[210],"exact":[213],"high-quality":[215],"approximate)":[216],"results":[217],"without":[218],"raising":[219],"requirements.":[221]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}