{"id":"https://openalex.org/W4393078719","doi":"https://doi.org/10.1109/tpami.2024.3380604","title":"Gradient-Based Instance-Specific Visual Explanations for Object Specification and Object Discrimination","display_name":"Gradient-Based Instance-Specific Visual Explanations for Object Specification and Object Discrimination","publication_year":2024,"publication_date":"2024-03-22","ids":{"openalex":"https://openalex.org/W4393078719","doi":"https://doi.org/10.1109/tpami.2024.3380604","pmid":"https://pubmed.ncbi.nlm.nih.gov/38517727"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3380604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3380604","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://scholars.cityu.edu.hk/en/publications/gradient-based-instance-specific-visual-explanations-for-object-s","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010958598","display_name":"Chenyang Zhao","orcid":"https://orcid.org/0000-0003-2233-8494"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chenyang Zhao","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-2233-8494","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079353328","display_name":"Janet H. Hsiao","orcid":"https://orcid.org/0000-0003-2271-8710"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Janet H. Hsiao","raw_affiliation_strings":["Division of Social Science, Hong Kong University of Science & Technology, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-2271-8710","affiliations":[{"raw_affiliation_string":"Division of Social Science, Hong Kong University of Science & Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065680386","display_name":"Antoni B. Chan","orcid":"https://orcid.org/0000-0002-2886-2513"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Antoni B. Chan","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-2886-2513","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.0178,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95684012,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"46","issue":"9","first_page":"5967","last_page":"5985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9983999729156494,"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":0.9983999729156494,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9965999722480774,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9950000047683716,"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/detector","display_name":"Detector","score":0.7204812169075012},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.715662956237793},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6621857285499573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6512816548347473},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5803248882293701},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5020251274108887},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4347073435783386},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38176682591438293}],"concepts":[{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.7204812169075012},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715662956237793},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6621857285499573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6512816548347473},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5803248882293701},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5020251274108887},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4347073435783386},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38176682591438293},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/tpami.2024.3380604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3380604","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"is_oa":true,"landing_page_url":"https://scholars.cityu.edu.hk/en/publications/gradient-based-instance-specific-visual-explanations-for-object-s","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:38517727","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38517727","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-137475","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-137475","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"},{"id":"pmh:oai:hub.hku.hk:10722/351192","is_oa":true,"landing_page_url":"https://hub.hku.hk/handle/10722/351192","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:pure.atira.dk:publications/cbe72029-fadc-42d1-a322-0b38a7488f98","is_oa":true,"landing_page_url":"https://hdl.handle.net/2031/cbe72029-fadc-42d1-a322-0b38a7488f98","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zhao, C, Hsiao, J H & Chan, A B 2024, 'Gradient-Based Instance-Specific Visual Explanations for Object Specification and Object Discrimination', IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 9, pp. 5967-5985. https://doi.org/10.1109/TPAMI.2024.3380604","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://scholars.cityu.edu.hk/en/publications/gradient-based-instance-specific-visual-explanations-for-object-s","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G7398854287","display_name":null,"funder_award_id":"7005995","funder_id":"https://openalex.org/F4320309893","funder_display_name":"City University of Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320309893","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":105,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1690739335","https://openalex.org/W1787224781","https://openalex.org/W1821462560","https://openalex.org/W1832500336","https://openalex.org/W1849277567","https://openalex.org/W1861492603","https://openalex.org/W2102605133","https://openalex.org/W2194775991","https://openalex.org/W2195388612","https://openalex.org/W2240067561","https://openalex.org/W2295107390","https://openalex.org/W2516809705","https://openalex.org/W2561238782","https://openalex.org/W2563296158","https://openalex.org/W2565639579","https://openalex.org/W2606462007","https://openalex.org/W2739879705","https://openalex.org/W2750432752","https://openalex.org/W2759653627","https://openalex.org/W2765793020","https://openalex.org/W2776207810","https://openalex.org/W2798405286","https://openalex.org/W2798542761","https://openalex.org/W2895739182","https://openalex.org/W2901505625","https://openalex.org/W2949725973","https://openalex.org/W2952787292","https://openalex.org/W2955192706","https://openalex.org/W2959289524","https://openalex.org/W2962851944","https://openalex.org/W2962858109","https://openalex.org/W2963037989","https://openalex.org/W2963091558","https://openalex.org/W2963140444","https://openalex.org/W2963150697","https://openalex.org/W2963260436","https://openalex.org/W2963351448","https://openalex.org/W2963371637","https://openalex.org/W2963609017","https://openalex.org/W2963714376","https://openalex.org/W2963769056","https://openalex.org/W2964080601","https://openalex.org/W2964111476","https://openalex.org/W2964121718","https://openalex.org/W2978017171","https://openalex.org/W2982220924","https://openalex.org/W2982242214","https://openalex.org/W2982560934","https://openalex.org/W2982770724","https://openalex.org/W2995607862","https://openalex.org/W3010219363","https://openalex.org/W3011684164","https://openalex.org/W3035253074","https://openalex.org/W3035323039","https://openalex.org/W3036321094","https://openalex.org/W3036370755","https://openalex.org/W3037256687","https://openalex.org/W3083155260","https://openalex.org/W3091981646","https://openalex.org/W3096609285","https://openalex.org/W3101609372","https://openalex.org/W3106153666","https://openalex.org/W3131500599","https://openalex.org/W3163696279","https://openalex.org/W3173270634","https://openalex.org/W3176196997","https://openalex.org/W3176459575","https://openalex.org/W3176482836","https://openalex.org/W3176692018","https://openalex.org/W3186608063","https://openalex.org/W3215626407","https://openalex.org/W4214524539","https://openalex.org/W4230405732","https://openalex.org/W4289751568","https://openalex.org/W4293861706","https://openalex.org/W4300235091","https://openalex.org/W4312956471","https://openalex.org/W4313141028","https://openalex.org/W4365601042","https://openalex.org/W6637551013","https://openalex.org/W6638523607","https://openalex.org/W6685133223","https://openalex.org/W6730179637","https://openalex.org/W6735632633","https://openalex.org/W6737947904","https://openalex.org/W6738549535","https://openalex.org/W6739575509","https://openalex.org/W6743188669","https://openalex.org/W6750697433","https://openalex.org/W6752170072","https://openalex.org/W6754719772","https://openalex.org/W6755523629","https://openalex.org/W6767259515","https://openalex.org/W6768851824","https://openalex.org/W6769906912","https://openalex.org/W6779478644","https://openalex.org/W6779613827","https://openalex.org/W6789011712","https://openalex.org/W6791353385","https://openalex.org/W6803872405","https://openalex.org/W6811013733","https://openalex.org/W6845643312","https://openalex.org/W6982426160"],"related_works":["https://openalex.org/W2366906938","https://openalex.org/W2349391998","https://openalex.org/W4205655149","https://openalex.org/W2000775715","https://openalex.org/W2795393339","https://openalex.org/W2626393719","https://openalex.org/W4390618967","https://openalex.org/W4386159726","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"We":[0,67,102],"propose":[1,196],"the":[2,15,21,28,38,43,93,115,119,139,151,154,163,168,211,225,233,236,244,256],"gradient-weighted":[3],"Object":[4],"Detector":[5],"Activation":[6],"Maps":[7],"(ODAM),":[8],"a":[9,135],"visual":[10,90,140,169],"explanation":[11,105,164,238],"technique":[12],"for":[13,46,107,118,220,239],"interpreting":[14],"predictions":[16,222],"of":[17,23,40,82,97,138,142,153,171,207,214,228,235],"object":[18,108,111,122,125,172,212,229,259],"detectors.":[19],"Utilizing":[20],"gradients":[22],"detector":[24,83],"targets":[25],"flowing":[26],"into":[27],"intermediate":[29],"feature":[30],"maps,":[31,165],"ODAM":[32,59,70,215],"produces":[33,88],"heat":[34],"maps":[35,57],"that":[36,69],"show":[37,68],"influence":[39],"regions":[41],"on":[42,54,162,203,258],"detector's":[44],"decision":[45],"each":[47,240],"predicted":[48],"attribute.":[49],"Compared":[50],"to":[51,73,149,216,242,254],"previous":[52],"works":[53],"classification":[55],"activation":[56],"(CAM),":[58],"generates":[60],"instance-specific":[61],"explanations":[62,91,141,170],"rather":[63],"than":[64,92],"class-specific":[65],"ones.":[66],"is":[71,114,126,188,252],"applicable":[72],"one-stage,":[74],"two-stage,":[75],"and":[76,85,87,100,144,184,200,223,261],"transformer-based":[77],"detectors":[78,143,173],"with":[79,175,190,263],"different":[80],"types":[81],"backbones":[84],"heads,":[86],"higher-quality":[89],"state-of-the-art":[94],"in":[95],"terms":[96],"both":[98],"effectiveness":[99,152],"efficiency.":[101],"discuss":[103],"two":[104,131,197,205],"tasks":[106],"detection:":[109],"1)":[110],"specification:":[112],"what":[113],"important":[116],"region":[117],"prediction?":[120],"2)":[121],"discrimination:":[123],"which":[124],"detected?":[127],"Aiming":[128],"at":[129],"these":[130,204],"aspects,":[132],"we":[133,158,194],"present":[134],"detailed":[136],"analysis":[137],"carry":[145],"out":[146],"extensive":[147],"experiments":[148],"validate":[150],"proposed":[155,253],"ODAM.":[156,208],"Furthermore,":[157],"investigate":[159],"user":[160,191],"trust":[161],"how":[166],"well":[167],"agrees":[174],"human":[176,181],"explanations,":[177],"as":[178],"measured":[179],"through":[180],"eye":[182],"gaze,":[183],"whether":[185],"this":[186],"agreement":[187],"related":[189],"trust.":[192],"Finally,":[193],"also":[195],"applications,":[198],"ODAM-KD":[199,209],"ODAM-NMS,":[201],"based":[202],"abilities":[206],"utilizes":[210],"specification":[213],"generate":[217],"top-down":[218],"attention":[219],"key":[221],"instruct":[224],"knowledge":[226],"distillation":[227],"detection.":[230],"ODAM-NMS":[231],"considers":[232],"location":[234],"model's":[237],"prediction":[241],"distinguish":[243],"duplicate":[245],"detected":[246],"objects.":[247],"A":[248],"training":[249],"scheme,":[250],"ODAM-Train,":[251],"improve":[255],"quality":[257],"discrimination,":[260],"help":[262],"ODAM-NMS.":[264]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}