{"id":"https://openalex.org/W4402916006","doi":"https://doi.org/10.1109/icip51287.2024.10647577","title":"Improving Image Coding for Machines Through Optimizing Encoder Via Auxiliary Loss","display_name":"Improving Image Coding for Machines Through Optimizing Encoder Via Auxiliary Loss","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402916006","doi":"https://doi.org/10.1109/icip51287.2024.10647577"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10647577","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip51287.2024.10647577","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5038000650","display_name":"Kei Iino","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kei Iino","raw_affiliation_strings":["Waseda University,Graduate School of Fundamental Science and Engineering,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of Fundamental Science and Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039867800","display_name":"Shunsuke Akamatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shunsuke Akamatsu","raw_affiliation_strings":["Waseda University,Graduate School of Fundamental Science and Engineering,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of Fundamental Science and Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025914451","display_name":"Hiroshi Watanabe","orcid":"https://orcid.org/0000-0003-1557-3015"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Watanabe","raw_affiliation_strings":["Waseda University,Graduate School of Fundamental Science and Engineering,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of Fundamental Science and Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036430329","display_name":"Shohei Enomoto","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shohei Enomoto","raw_affiliation_strings":["NTT Software Innovation Center,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Software Innovation Center,Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042173462","display_name":"Akira Sakamoto","orcid":"https://orcid.org/0000-0002-4646-1318"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Akira Sakamoto","raw_affiliation_strings":["NTT Software Innovation Center,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Software Innovation Center,Tokyo,Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019776988","display_name":"Takeharu Eda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takeharu Eda","raw_affiliation_strings":["NTT Software Innovation Center,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Software Innovation Center,Tokyo,Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18733394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"3771","last_page":"3777"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.6779000163078308,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12002","display_name":"Computability, Logic, AI Algorithms","score":0.6779000163078308,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/encoder","display_name":"Encoder","score":0.7054823637008667},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6592690944671631},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5695515275001526},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3266216516494751},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1580212414264679},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.059945136308670044}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7054823637008667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6592690944671631},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5695515275001526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3266216516494751},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1580212414264679},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.059945136308670044},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10647577","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip51287.2024.10647577","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2125215748","https://openalex.org/W2194775991","https://openalex.org/W2339172597","https://openalex.org/W2549139847","https://openalex.org/W2952122856","https://openalex.org/W2963661664","https://openalex.org/W2964309882","https://openalex.org/W3034469748","https://openalex.org/W3107847925","https://openalex.org/W3160673571","https://openalex.org/W3171673455","https://openalex.org/W4224134719","https://openalex.org/W4280603646","https://openalex.org/W4308233977","https://openalex.org/W4317555115","https://openalex.org/W4386075611","https://openalex.org/W4389474451","https://openalex.org/W6620707391","https://openalex.org/W6756732229","https://openalex.org/W6779631978","https://openalex.org/W6785680213","https://openalex.org/W6810363922"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2366163563","https://openalex.org/W2163885456"],"abstract_inverted_index":{"Image":[0],"coding":[1],"for":[2,9,25,35,105],"machines":[3],"(ICM)":[4],"aims":[5],"to":[6,28,113,116,145],"compress":[7,31],"images":[8],"machine":[10,37],"analysis":[11],"using":[12],"recognition":[13,38,72,83,119],"models":[14,108],"rather":[15],"than":[16],"human":[17],"vision.":[18],"Hence,":[19],"in":[20,45,137],"ICM,":[21],"it":[22],"is":[23,85],"important":[24],"the":[26,32,36,50,68,71,82,114,146],"encoder":[27,69,115],"recognize":[29],"and":[30,57,87,121,134,140],"information":[33],"necessary":[34],"task.":[39],"There":[40],"are":[41],"two":[42],"main":[43],"approaches":[44,66],"learned":[46,106],"ICM;":[47],"optimization":[48,75],"of":[49,59,131],"compression":[51],"model":[52,84],"based":[53,62],"on":[54],"task":[55,77],"loss,":[56],"Region":[58],"Interest":[60],"(ROI)":[61],"bit":[63],"allocation.":[64],"These":[65],"provide":[67],"with":[70,76],"capability.":[73],"However,":[74],"loss":[78,112],"becomes":[79],"difficult":[80],"when":[81],"deep,":[86],"ROI-based":[88],"methods":[89],"often":[90],"involve":[91],"extra":[92],"overhead":[93],"during":[94],"evaluation.":[95],"In":[96],"this":[97],"study,":[98],"we":[99],"propose":[100],"a":[101],"novel":[102],"training":[103,148],"method":[104,125],"ICM":[107],"that":[109],"applies":[110],"auxiliary":[111],"improve":[117],"its":[118],"capability":[120],"rate-distortion":[122],"performance.":[123],"Our":[124],"achieves":[126],"Bj\u00f8ntegaard":[127],"Delta":[128],"rate":[129],"improvements":[130],"$27.7":[132],"\\%$":[133,136],"$20.3":[135],"object":[138],"detection":[139],"semantic":[141],"segmentation":[142],"tasks,":[143],"compared":[144],"conventional":[147],"method.":[149]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}