{"id":"https://openalex.org/W3193308254","doi":"https://doi.org/10.1109/icip42928.2021.9506754","title":"A Unified Density-Driven Framework For Effective Data Denoising And Robust Abstention","display_name":"A Unified Density-Driven Framework For Effective Data Denoising And Robust Abstention","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3193308254","doi":"https://doi.org/10.1109/icip42928.2021.9506754","mag":"3193308254"},"language":"en","primary_location":{"id":"doi:10.1109/icip42928.2021.9506754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506754","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/A5081081395","display_name":"Krishanu Sarker","orcid":null},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishanu Sarker","raw_affiliation_strings":["Georgia State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia State University","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102826162","display_name":"Xiulong Yang","orcid":"https://orcid.org/0000-0003-3417-7106"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiulong Yang","raw_affiliation_strings":["Georgia State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia State University","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695665","display_name":"Yang Li","orcid":"https://orcid.org/0000-0002-3410-7856"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["Georgia State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia State University","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038120331","display_name":"Saeid Belkasim","orcid":null},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saeid Belkasim","raw_affiliation_strings":["Georgia State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia State University","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036338045","display_name":"Shihao Ji","orcid":"https://orcid.org/0000-0002-3573-5379"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shihao Ji","raw_affiliation_strings":["Georgia State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia State University","institution_ids":["https://openalex.org/I181565077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.11185001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"594","last_page":"598"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9995999932289124,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9995999932289124,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9994999766349792,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.7678612470626831},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6839882731437683},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5767589807510376},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.562025785446167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5605072975158691},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5372025966644287},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5361129641532898},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5187780857086182},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4555765688419342},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44761449098587036},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43223050236701965},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.4305092692375183},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.42179766297340393},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.09733757376670837},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06096756458282471}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678612470626831},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6839882731437683},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5767589807510376},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.562025785446167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5605072975158691},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5372025966644287},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5361129641532898},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5187780857086182},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4555765688419342},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44761449098587036},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43223050236701965},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4305092692375183},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.42179766297340393},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.09733757376670837},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06096756458282471},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip42928.2021.9506754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506754","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":[{"id":"https://metadata.un.org/sdg/9","score":0.6100000143051147,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1673310716","https://openalex.org/W1686810756","https://openalex.org/W1994550352","https://openalex.org/W2116458520","https://openalex.org/W2117539524","https://openalex.org/W2133059825","https://openalex.org/W2133564696","https://openalex.org/W2137560901","https://openalex.org/W2161813894","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2335728318","https://openalex.org/W2577784528","https://openalex.org/W2743200750","https://openalex.org/W2750384547","https://openalex.org/W2767414122","https://openalex.org/W2867167548","https://openalex.org/W2890123008","https://openalex.org/W2903914089","https://openalex.org/W2946376679","https://openalex.org/W2951394837","https://openalex.org/W2953793718","https://openalex.org/W2963096987","https://openalex.org/W3020972252","https://openalex.org/W3105081694","https://openalex.org/W3118608800","https://openalex.org/W6637131181","https://openalex.org/W6637373629","https://openalex.org/W6676971654","https://openalex.org/W6679434410","https://openalex.org/W6684105480","https://openalex.org/W6740005241","https://openalex.org/W6742511895","https://openalex.org/W6743688258","https://openalex.org/W6745891213","https://openalex.org/W6752760542","https://openalex.org/W6754684794","https://openalex.org/W6759230470","https://openalex.org/W6762619493","https://openalex.org/W6767099221","https://openalex.org/W6767354347","https://openalex.org/W6774960221","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W209733029","https://openalex.org/W2891480213","https://openalex.org/W3000197790","https://openalex.org/W3118953353","https://openalex.org/W2158542502","https://openalex.org/W1997978958","https://openalex.org/W133774893","https://openalex.org/W2099971677","https://openalex.org/W2250522181","https://openalex.org/W2615667245"],"abstract_inverted_index":{"The":[0],"success":[1],"of":[2,17,84],"Deep":[3],"Neural":[4],"Networks":[5],"(DNNs)":[6],"highly":[7],"depends":[8],"on":[9,73],"data":[10,40,46,61,94],"quality.":[11],"Moreover,":[12],"predictive":[13],"uncertainty":[14],"reduces":[15],"reliability":[16],"DNNs":[18],"for":[19],"real-world":[20],"applications.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25],"aim":[26],"to":[27],"address":[28],"these":[29],"two":[30],"issues":[31],"by":[32],"proposing":[33],"a":[34],"unified":[35],"filtering":[36],"framework":[37,56,86],"leveraging":[38],"underlying":[39],"density,":[41],"that":[42],"effectively":[43],"denoises":[44],"training":[45,93],"as":[47,49],"well":[48],"avoids":[50],"predicting":[51],"confusing":[52],"samples.":[53],"Our":[54],"proposed":[55],"differentiates":[57],"noise":[58],"from":[59],"clean":[60],"samples":[62],"without":[63],"modifying":[64],"existing":[65],"DNN":[66],"architectures":[67],"or":[68],"loss":[69],"functions.":[70],"Extensive":[71],"experiments":[72],"multiple":[74],"benchmark":[75],"datasets":[76],"and":[77,95],"recent":[78],"COVIDx":[79],"dataset":[80],"demonstrate":[81],"the":[82],"effectiveness":[83],"our":[85],"over":[87],"state-of-the-art":[88],"(SOTA)":[89],"methods":[90],"in":[91],"denoising":[92],"abstaining":[96],"uncertain":[97],"test":[98],"data.":[99]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}