{"id":"https://openalex.org/W4311638103","doi":"https://doi.org/10.48550/arxiv.2212.07372","title":"Image Compression with Product Quantized Masked Image Modeling","display_name":"Image Compression with Product Quantized Masked Image Modeling","publication_year":2022,"publication_date":"2022-12-14","ids":{"openalex":"https://openalex.org/W4311638103","doi":"https://doi.org/10.48550/arxiv.2212.07372"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2212.07372","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.07372","pdf_url":"https://arxiv.org/pdf/2212.07372","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2212.07372","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083505661","display_name":"Alaaeldin El-Nouby","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"El-Nouby, Alaaeldin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029739727","display_name":"Matthew J. Muckley","orcid":"https://orcid.org/0000-0002-6525-8817"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muckley, Matthew J.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058031547","display_name":"Karen Ullrich","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ullrich, Karen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087781064","display_name":"Ivan Laptev","orcid":"https://orcid.org/0000-0001-7072-3325"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laptev, Ivan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040312210","display_name":"Jakob Verbeek","orcid":"https://orcid.org/0000-0003-1419-1816"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Verbeek, Jakob","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111802678","display_name":"Herv\u00e9 Je\u01f5ou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J\u00e9gou, Herv\u00e9","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.996999979019165,"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"}},"topics":[{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.996999979019165,"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":0.9968000054359436,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.991599977016449,"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/vector-quantization","display_name":"Vector quantization","score":0.7376353740692139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6207201480865479},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.6154639720916748},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.5731348395347595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5200088620185852},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4936131238937378},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4693758487701416},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43575167655944824},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3596777617931366},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.25695091485977173},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.22215205430984497}],"concepts":[{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.7376353740692139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6207201480865479},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.6154639720916748},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.5731348395347595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5200088620185852},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4936131238937378},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4693758487701416},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43575167655944824},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3596777617931366},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25695091485977173},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.22215205430984497}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2212.07372","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.07372","pdf_url":"https://arxiv.org/pdf/2212.07372","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2212.07372","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2212.07372","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2212.07372","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.07372","pdf_url":"https://arxiv.org/pdf/2212.07372","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2148772884","https://openalex.org/W2017514583","https://openalex.org/W2100120615","https://openalex.org/W2147406819","https://openalex.org/W2352648934","https://openalex.org/W1929869830","https://openalex.org/W2387054321","https://openalex.org/W2017401491","https://openalex.org/W2062765737","https://openalex.org/W2012827167"],"abstract_inverted_index":{"Recent":[0],"neural":[1],"compression":[2,22,159,206,222],"methods":[3],"have":[4],"been":[5],"based":[6],"on":[7,14,161],"the":[8,64,74,114,122,144,147,220],"popular":[9],"hyperprior":[10,165],"framework.":[11],"It":[12,99,167],"relies":[13],"Scalar":[15],"Quantization":[16,37],"and":[17,32,67,87,127,175,207],"offers":[18],"a":[19,79,92,133,202,216,235],"very":[20],"strong":[21],"performance.":[23],"This":[24,82],"contrasts":[25],"from":[26],"recent":[27,164],"advances":[28],"in":[29,121,171],"image":[30,59,129,191,226],"generation":[31,192],"representation":[33],"learning,":[34],"where":[35,224],"Vector":[36],"is":[38,155,188,227],"more":[39],"commonly":[40],"employed.":[41],"In":[42],"this":[43],"work,":[44],"we":[45,72,131,194,218],"attempt":[46],"to":[47],"bring":[48],"these":[49],"lines":[50],"of":[51,96,116,124,146,173],"research":[52],"closer":[53],"by":[54,78,113,142],"revisiting":[55],"vector":[56,76,86],"quantization":[57,89],"for":[58,91],"compression.":[60],"We":[61],"build":[62],"upon":[63],"VQ-VAE":[65],"framework":[66],"introduce":[68],"several":[69],"modifications.":[70],"First,":[71],"replace":[73],"vanilla":[75],"quantizer":[77],"product":[80],"quantizer.":[81],"intermediate":[83],"solution":[84],"between":[85,205],"scalar":[88],"allows":[90],"much":[93],"wider":[94],"set":[95],"rate-distortion":[97],"points:":[98],"implicitly":[100],"defines":[101],"high-quality":[102],"quantizers":[103],"that":[104,197],"would":[105],"otherwise":[106],"require":[107],"intractably":[108],"large":[109],"codebooks.":[110],"Second,":[111],"inspired":[112],"success":[115],"Masked":[117],"Image":[118],"Modeling":[119],"(MIM)":[120],"context":[123],"self-supervised":[125],"learning":[126],"generative":[128],"models,":[130],"propose":[132],"novel":[134],"conditional":[135],"entropy":[136,140],"model":[137,154],"which":[138],"improves":[139],"coding":[141],"modelling":[143],"co-dependencies":[145],"quantized":[148],"latent":[149],"codes.":[150],"The":[151],"resulting":[152],"PQ-MIM":[153,187],"surprisingly":[156],"effective:":[157],"its":[158],"performance":[160],"par":[162],"with":[163,180,190,209],"methods.":[166],"also":[168],"outperforms":[169],"HiFiC":[170],"terms":[172],"FID":[174],"KID":[176],"metrics":[177],"when":[178],"optimized":[179],"perceptual":[181],"losses":[182],"(e.g.":[183],"adversarial).":[184],"Finally,":[185],"since":[186],"compatible":[189],"frameworks,":[193],"show":[195],"qualitatively":[196],"it":[198],"can":[199],"operate":[200],"under":[201],"hybrid":[203],"mode":[204],"generation,":[208],"no":[210],"further":[211],"training":[212],"or":[213],"finetuning.":[214],"As":[215],"result,":[217],"explore":[219],"extreme":[221],"regime":[223],"an":[225],"compressed":[228],"into":[229],"200":[230],"bytes,":[231],"i.e.,":[232],"less":[233],"than":[234],"tweet.":[236]},"counts_by_year":[{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":3}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}