{"id":"https://openalex.org/W3195542584","doi":"https://doi.org/10.1109/icip42928.2021.9506118","title":"Class Specific Interpretability in CNN Using Causal Analysis","display_name":"Class Specific Interpretability in CNN Using Causal Analysis","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3195542584","doi":"https://doi.org/10.1109/icip42928.2021.9506118","mag":"3195542584"},"language":"en","primary_location":{"id":"doi:10.1109/icip42928.2021.9506118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","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/A5084525298","display_name":"Ankit Yadu","orcid":"https://orcid.org/0000-0001-5926-0876"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ankit Yadu","raw_affiliation_strings":["Samsung R&D India,Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung R&D India,Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042939692","display_name":"P K Suhas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"P K Suhas","raw_affiliation_strings":["Samsung R&D India,Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung R&D India,Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014371833","display_name":"Neelam Sinha","orcid":"https://orcid.org/0000-0001-8164-8412"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Neelam Sinha","raw_affiliation_strings":["International Institute of Information Technology,Bangalore","International Institute of Information Technology, Bangalore"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology,Bangalore","institution_ids":["https://openalex.org/I181514455"]},{"raw_affiliation_string":"International Institute of Information Technology, Bangalore","institution_ids":["https://openalex.org/I181514455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084525298"],"corresponding_institution_ids":["https://openalex.org/I4210139030"],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78237764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3702","last_page":"3706"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","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/T11689","display_name":"Adversarial Robustness in Machine Learning","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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9968000054359436,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9876999855041504,"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/interpretability","display_name":"Interpretability","score":0.9470338821411133},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6540799736976624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6165452003479004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46574246883392334},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35485631227493286}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9470338821411133},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6540799736976624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6165452003479004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46574246883392334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35485631227493286}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip42928.2021.9506118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1664049007","https://openalex.org/W1787224781","https://openalex.org/W2049910836","https://openalex.org/W2117539524","https://openalex.org/W2143891888","https://openalex.org/W2282821441","https://openalex.org/W2594633041","https://openalex.org/W2605409611","https://openalex.org/W2766204142","https://openalex.org/W2902340407","https://openalex.org/W2962807820","https://openalex.org/W2963781258","https://openalex.org/W2972006294","https://openalex.org/W2978768213","https://openalex.org/W2981731882","https://openalex.org/W2992613109","https://openalex.org/W3009431628","https://openalex.org/W3026235644","https://openalex.org/W3103526964","https://openalex.org/W3133427233","https://openalex.org/W4288600473","https://openalex.org/W4295253939","https://openalex.org/W4298193105","https://openalex.org/W4301592166","https://openalex.org/W6736518430","https://openalex.org/W6758720947"],"related_works":["https://openalex.org/W1986582023","https://openalex.org/W2961085424","https://openalex.org/W2966829450","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694"],"abstract_inverted_index":{"A":[0],"singular":[1],"problem":[2],"that":[3,35,173],"mars":[4],"the":[5,14,57,63,67,89,92,96,107,186,191,194,198,207,213],"wide":[6],"applicability":[7],"of":[8,16,39,66,91,95,102,106,152,206],"machine":[9],"learning":[10],"(ML)":[11],"models":[12],"is":[13,23,54,110],"lack":[15],"generalizability":[17],"and":[18,117,160,210],"interpretability.":[19],"The":[20,104,140,181],"ML":[21],"community":[22],"increasingly":[24],"working":[25],"on":[26,112,136],"bridging":[27],"this":[28,50],"gap.":[29],"Prominent":[30],"among":[31],"them":[32],"are":[33,144],"methods":[34],"study":[36],"causal":[37,58],"significance":[38,64],"features,":[40],"with":[41],"techniques":[42],"such":[43],"as":[44,178],"Average":[45],"Causal":[46],"Effect":[47],"(ACE).":[48],"In":[49],"paper,":[51],"our":[52],"objective":[53],"to":[55,61,146,184],"utilize":[56],"analysis":[59],"framework":[60],"measure":[62],"level":[65],"features":[68],"in":[69,203],"binary":[70,128],"classification":[71,129],"task.":[72],"Towards":[73],"this,":[74],"we":[75],"propose":[76],"a":[77],"novel":[78],"ACE-based":[79],"metric":[80,109,142,188,201],"called":[81],"\u201cAbsolute":[82],"area":[83,90],"under":[84],"ACE":[85,97],"(A-ACE)\u201d":[86],"which":[87,189],"computes":[88],"absolute":[93],"value":[94],"across":[98],"different":[99],"permissible":[100],"levels":[101],"intervention.":[103],"performance":[105,151],"proposed":[108],"illustrated":[111],"(i)":[113],"ILSVRC":[114,158],"(Imagenet)":[115],"dataset":[116,159,167],"(ii)":[118],"MNIST":[119,166],"data":[120],"set":[121],"$(\\sim":[122],"42000$":[123],"images)":[124],"by":[125,197],"considering":[126],"pair-wise":[127],"problem.":[130],"Encouraging":[131],"results":[132],"have":[133],"been":[134],"observed":[135],"these":[137],"two":[138],"datasets.":[139],"computed":[141],"values":[143],"found":[145],"be":[147],"higher":[148,154,162],"-":[149,168],"peak":[150],"10x":[153],"than":[155,163],"other":[156],"for":[157,165],"50%":[161],"others":[164],"at":[169],"precisely":[170],"those":[171],"locations":[172],"human":[174],"intuition":[175],"would":[176],"mark":[177],"distinguishing":[179],"regions.":[180],"method":[182],"helps":[183],"capture":[185],"quantifiable":[187],"represents":[190],"distinction":[192],"between":[193],"classes":[195],"learnt":[196],"model.":[199],"This":[200],"aids":[202],"visual":[204],"explanation":[205],"model\u2019s":[208],"prediction":[209],"thus,":[211],"makes":[212],"model":[214],"more":[215],"trustworthy.":[216]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}