{"id":"https://openalex.org/W4414383836","doi":"https://doi.org/10.1109/iccv51701.2025.01717","title":"USP: Unified Self-Supervised Pretraining for Image Generation and Understanding","display_name":"USP: Unified Self-Supervised Pretraining for Image Generation and Understanding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414383836","doi":"https://doi.org/10.1109/iccv51701.2025.01717"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01717","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.06132","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101512474","display_name":"Xiangxiang Chu","orcid":"https://orcid.org/0000-0003-2548-0605"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiangxiang Chu","raw_affiliation_strings":["AMAP, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMAP, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102799776","display_name":"Renda Li","orcid":"https://orcid.org/0009-0002-3611-2840"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Renda Li","raw_affiliation_strings":["AMAP, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMAP, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100424366","display_name":"Yong Wang","orcid":"https://orcid.org/0000-0001-7670-3958"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Wang","raw_affiliation_strings":["AMAP, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AMAP, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101512474"],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2272664,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18475","last_page":"18486"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.7386000156402588,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.7386000156402588,"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/T10320","display_name":"Neural Networks and Applications","score":0.6984999775886536,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6773999929428101},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6597999930381775},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6495000123977661},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5422000288963318},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4560999870300293},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43320000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7218000292778015},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6773999929428101},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6597999930381775},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6495000123977661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.626800000667572},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5422000288963318},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4560999870300293},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4496000111103058},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4002000093460083},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.3698999881744385},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34049999713897705},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2791000008583069}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01717","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01717","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:2503.06132","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.06132","pdf_url":"https://arxiv.org/pdf/2503.06132","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2503.06132","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.06132","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.06132","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.06132","pdf_url":"https://arxiv.org/pdf/2503.06132","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"highlighted":[3],"the":[4,30,55,97],"interplay":[5],"between":[6],"diffusion":[7,15,36,46,74,104],"models":[8,16,27,44,47,75],"and":[9,32,54,100],"representation":[10],"learning.":[11],"Intermediate":[12],"representations":[13],"from":[14,42],"can":[17,28],"be":[18,109],"leveraged":[19],"for":[20],"downstream":[21],"visual":[22],"tasks,":[23],"while":[24,94],"self-supervised":[25],"vision":[26,43],"enhance":[29],"convergence":[31,98],"generation":[33,101],"quality":[34,102],"of":[35,57,103],"models.":[37,105],"However,":[38],"transferring":[39],"pretrained":[40],"weights":[41],"to":[45,51],"is":[48],"challenging":[49],"due":[50],"input":[52],"mismatches":[53],"use":[56],"latent":[58,78,85],"spaces.":[59],"To":[60],"address":[61],"these":[62],"challenges,":[63],"we":[64],"propose":[65],"Unified":[66],"Self-supervised":[67],"Pretraining":[68],"(USP),":[69],"a":[70,81],"framework":[71],"that":[72],"initializes":[73],"via":[76],"masked":[77],"modeling":[79],"in":[80,91],"Variational":[82],"Autoencoder":[83],"(VAE)":[84],"space.":[86],"USP":[87],"achieves":[88],"comparable":[89],"performance":[90],"understanding":[92],"tasks":[93],"significantly":[95],"improving":[96],"speed":[99],"Our":[106],"code":[107],"will":[108],"publicly":[110],"available":[111],"at":[112],"https://github.com/AMAP-ML/USP.":[113]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}