{"id":"https://openalex.org/W4404353549","doi":"https://doi.org/10.1109/iccv51701.2025.02132","title":"Addressing Representation Collapse in Vector Quantized Models with One Linear Layer","display_name":"Addressing Representation Collapse in Vector Quantized Models with One Linear Layer","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404353549","doi":"https://doi.org/10.1109/iccv51701.2025.02132"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02132","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.02038","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086260915","display_name":"Yongxin Zhu","orcid":"https://orcid.org/0000-0002-1813-1792"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongxin Zhu","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014439450","display_name":"Bocheng Li","orcid":"https://orcid.org/0009-0007-7701-627X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bocheng Li","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040345182","display_name":"Yifei Xin","orcid":"https://orcid.org/0000-0001-9104-8277"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifei Xin","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhihua Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhihua Xia","raw_affiliation_strings":["Jinan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jinan University","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Linli Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linli Xu","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"22968","last_page":"22977"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.32190001010894775,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.32190001010894775,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.3021000027656555,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.26910001039505005,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6312296390533447},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4551522433757782},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4093868136405945},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.37350618839263916},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3555377721786499},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.20361194014549255},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.1110498309135437},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.08412793278694153},{"id":"https://openalex.org/keywords/politics","display_name":"Politics","score":0.07302170991897583},{"id":"https://openalex.org/keywords/nanotechnology","display_name":"Nanotechnology","score":0.07143193483352661}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6312296390533447},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4551522433757782},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4093868136405945},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.37350618839263916},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3555377721786499},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.20361194014549255},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.1110498309135437},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.08412793278694153},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.07302170991897583},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.07143193483352661}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02132","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.02038","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.02038","pdf_url":"https://arxiv.org/pdf/2411.02038","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.02038","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.02038","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:2411.02038","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.02038","pdf_url":"https://arxiv.org/pdf/2411.02038","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G544562989","display_name":null,"funder_award_id":"62276245","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404353549.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027"],"abstract_inverted_index":{"Vector":[0],"Quantization":[1],"(VQ)":[2],"is":[3,104,131,144],"essential":[4],"for":[5],"discretizing":[6],"continuous":[7],"representations":[8],"in":[9],"unsupervised":[10],"learning":[11],"but":[12],"suffers":[13],"from":[14],"representation":[15],"collapse,":[16],"causing":[17],"low":[18],"codebook":[19,53,129],"utilization":[20],"and":[21,39,122,135,140],"limiting":[22],"scalability.":[23],"Existing":[24],"solutions":[25],"often":[26],"rely":[27],"on":[28,120],"complex":[29],"optimizations":[30],"or":[31],"reduce":[32],"latent":[33,84],"dimensionality,":[34],"which":[35,72],"compromises":[36],"model":[37],"capacity":[38],"fails":[40],"to":[41,106,133],"fully":[42],"solve":[43],"the":[44,48,87,98],"problem.":[45],"We":[46],"identify":[47],"root":[49],"cause":[50],"as":[51],"disjoint":[52],"optimization,":[54],"where":[55],"only":[56],"a":[57,77,83,108],"few":[58],"code":[59,74,95,143],"vectors":[60,75],"are":[61],"updated":[62],"via":[63],"gradient":[64],"descent.":[65],"To":[66],"fix":[67],"this,":[68],"we":[69],"propose":[70],"\\textbf{Sim}ple\\textbf{VQ},":[71],"reparameterizes":[73],"through":[76],"learnable":[78],"linear":[79,89,102,110],"transformation":[80],"layer":[81],"over":[82],"basis,":[85],"optimizing":[86],"\\textit{entire":[88],"space}":[90],"rather":[91],"than":[92],"nearest":[93],"\\textit{individual":[94],"vectors}.":[96],"Although":[97],"multiplication":[99],"of":[100],"two":[101],"matrices":[103],"equivalent":[105],"applying":[107],"single":[109],"layer,":[111],"this":[112],"simple":[113],"approach":[114],"effectively":[115],"prevents":[116],"collapse.":[117],"Extensive":[118],"experiments":[119],"image":[121],"audio":[123],"tasks":[124],"demonstrate":[125],"that":[126],"SimVQ":[127],"improves":[128],"usage,":[130],"easy":[132],"implement,":[134],"generalizes":[136],"well":[137],"across":[138],"modalities":[139],"architectures.":[141],"The":[142],"available":[145],"at":[146],"https://github.com/youngsheen/SimVQ.":[147]},"counts_by_year":[],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}
