{"id":"https://openalex.org/W4414360236","doi":"https://doi.org/10.24963/ijcai.2025/978","title":"DisPIM: Distilling PreTrained Image Models for Generalizable Visuo-Motor Control","display_name":"DisPIM: Distilling PreTrained Image Models for Generalizable Visuo-Motor Control","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360236","doi":"https://doi.org/10.24963/ijcai.2025/978"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/978","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/978","pdf_url":"https://www.ijcai.org/proceedings/2025/0978.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2025/0978.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101434309","display_name":"Haitao Wang","orcid":"https://orcid.org/0000-0001-9900-8528"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Wang","raw_affiliation_strings":["Guangdong Key Laboratory of Big Data Analysis and Processing","School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Big Data Analysis and Processing","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102755158","display_name":"Hejun Wu","orcid":"https://orcid.org/0000-0001-9758-5698"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hejun Wu","raw_affiliation_strings":["Guangdong Key Laboratory of Big Data Analysis and Processing","School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Big Data Analysis and Processing","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26435526,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8796","last_page":"8804"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9189000129699707,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9189000129699707,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9082000255584717,"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/generalization","display_name":"Generalization","score":0.8429999947547913},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.7416999936103821},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6664999723434448},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5843999981880188},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5613999962806702},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5566999912261963},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5299000144004822},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5073000192642212}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8429999947547913},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.7416999936103821},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7412999868392944},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6664999723434448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6554999947547913},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5843999981880188},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5613999962806702},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5566999912261963},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5299000144004822},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5073000192642212},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44670000672340393},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3718999922275543},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3357999920845032},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/978","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/978","pdf_url":"https://www.ijcai.org/proceedings/2025/0978.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2025/978","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/978","pdf_url":"https://www.ijcai.org/proceedings/2025/0978.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3373226507","display_name":null,"funder_award_id":"62272497","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414360236.pdf","grobid_xml":"https://content.openalex.org/works/W4414360236.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"DisPIM,":[2],"a":[3,20,44,78,85,116,160,165],"framework":[4],"that":[5,36,88],"leverages":[6],"pretrained":[7],"image":[8],"models":[9],"(PIMs)":[10],"for":[11,50,64,102,107],"visuo-motor":[12,17,51,103],"control.":[13,104],"Applying":[14],"PIMs":[15,48,96],"to":[16,24,42,69,137],"control":[18,52,158],"faces":[19],"big":[21],"difficulty":[22],"due":[23],"the":[25,29,38,55,92,132,139],"distribution":[26,30,45],"shift":[27],"between":[28],"of":[31,37,57,95,115,141,167],"visual":[32],"environmental":[33],"states":[34],"and":[35,143,156,171,177,187],"pretraining":[39],"datasets.":[40],"Due":[41],"such":[43],"shift,":[46],"fine-tuning":[47],"specifically":[49],"may":[53],"hurt":[54],"generalizability":[56],"PIMs,":[58],"while":[59],"adding":[60],"additional":[61],"tunable":[62],"parameters":[63],"specific":[65],"actions":[66],"apparently":[67],"lead":[68],"high":[70],"computational":[71,192],"costs.":[72],"DisPIM":[73,152,181],"addresses":[74],"these":[75],"challenges":[76],"using":[77],"novel":[79],"feature":[80],"distillation":[81,133],"approach,":[82],"which":[83,120],"obtains":[84],"compact":[86],"model":[87],"not":[89],"only":[90],"inherit":[91],"generalization":[93,142,186],"capability":[94],"but":[97],"also":[98],"acquire":[99],"task-specific":[100,144,155],"skills":[101],"This":[105,126],"good":[106],"both":[108,154,175],"sides":[109],"is":[110,121],"mainly":[111],"achieved":[112],"by":[113,123],"means":[114],"target":[117],"Q-ensemble":[118,127],"mechanism,":[119,151],"inspired":[122],"double":[124],"Q-learning.":[125],"mechanism":[128],"can":[129],"adaptively":[130],"adjust":[131],"rate,":[134],"so":[135],"as":[136],"balance":[138],"objective":[140],"ability":[145],"during":[146],"training.":[147],"With":[148],"this":[149],"balancing":[150],"achieves":[153],"generalizable":[157],"requiring":[159],"low":[161,191],"computation":[162],"cost.":[163],"Across":[164],"series":[166],"algorithms,":[168],"task":[169],"domains,":[170],"evaluation":[172],"metrics":[173],"in":[174,185],"simulation":[176],"real":[178],"robot,":[179],"our":[180],"demonstrates":[182],"significant":[183],"improvements":[184],"overall":[188],"performance":[189],"with":[190],"overhead.":[193]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}