{"id":"https://openalex.org/W4401023960","doi":"https://doi.org/10.24963/ijcai.2024/141","title":"RoboFusion: Towards Robust Multi-Modal 3D Object Detection via SAM","display_name":"RoboFusion: Towards Robust Multi-Modal 3D Object Detection via SAM","publication_year":2024,"publication_date":"2024-07-26","ids":{"openalex":"https://openalex.org/W4401023960","doi":"https://doi.org/10.24963/ijcai.2024/141"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2024/141","doi":"https://doi.org/10.24963/ijcai.2024/141","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2024/141","pdf_url":"https://www.ijcai.org/proceedings/2024/0141.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W4401023960"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2024/0141.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152041915","display_name":"Ziying Song","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziying Song","raw_affiliation_strings":["Beijing Key Lab of Traffic Data Analysis and Mining, China","School of Computer Science and Technology,Beijing Jiaotong University;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Lab of Traffic Data Analysis and Mining, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Technology,Beijing Jiaotong University;","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101616458","display_name":"Guoxing Zhang","orcid":"https://orcid.org/0000-0002-5566-2517","observed_orcids":["https://orcid.org/0000-0002-5566-2517"]},"institutions":[{"id":"https://openalex.org/I34155123","display_name":"Hebei University of Science and Technology","ror":"https://ror.org/05h3pkk68","country_code":"CN","type":"education","lineage":["https://openalex.org/I34155123"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoxing Zhang","raw_affiliation_strings":["Hebei University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hebei University of Science and Technology","institution_ids":["https://openalex.org/I34155123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151996752","display_name":"Lin Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Liu","raw_affiliation_strings":["Beijing Key Lab of Traffic Data Analysis and Mining, China","School of Computer Science and Technology,Beijing Jiaotong University;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Lab of Traffic Data Analysis and Mining, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Technology,Beijing Jiaotong University;","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152002353","display_name":"Lei Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Yang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138803596","display_name":"Shaoqing Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Shaoqing Xu","raw_affiliation_strings":["University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085282915","display_name":"Caiyan Jia","orcid":"https://orcid.org/0000-0003-0650-9564","observed_orcids":["https://orcid.org/0000-0003-0650-9564"]},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caiyan Jia","raw_affiliation_strings":["Beijing Key Lab of Traffic Data Analysis and Mining, China","School of Computer Science and Technology,Beijing Jiaotong University;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Lab of Traffic Data Analysis and Mining, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Technology,Beijing Jiaotong University;","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023071161","display_name":"Feiyang Jia","orcid":"https://orcid.org/0000-0001-9933-872X","observed_orcids":["https://orcid.org/0000-0001-9933-872X"]},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feiyang Jia","raw_affiliation_strings":["Beijing Key Lab of Traffic Data Analysis and Mining, China","School of Computer Science and Technology,Beijing Jiaotong University;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Lab of Traffic Data Analysis and Mining, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Technology,Beijing Jiaotong University;","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5151999716","display_name":"Li Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Wang","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.8482,"has_fulltext":true,"cited_by_count":56,"citation_normalized_percentile":{"value":0.98074361,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1272","last_page":"1280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5522000193595886,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.5522000193595886,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.41359999775886536,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.009200000204145908,"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/segment-anything-model","display_name":"Segment Anything Model","score":0.9290000200271606},{"id":"https://openalex.org/keywords/vision-foundation-models","display_name":"vision foundation models","score":0.9319999814033508},{"id":"https://openalex.org/keywords/autonomous-driving-perception","display_name":"autonomous driving perception","score":0.9430000185966492},{"id":"https://openalex.org/keywords/out-of-distribution-robustness","display_name":"out-of-distribution robustness","score":0.9129999876022339},{"id":"https://openalex.org/keywords/wavelet-decomposition","display_name":"wavelet decomposition","score":0.9869999885559082},{"id":"https://openalex.org/keywords/feature-fusion","display_name":"feature fusion","score":0.5889999866485596},{"id":"https://openalex.org/keywords/self-attention","display_name":"self-attention","score":0.8029999732971191},{"id":"https://openalex.org/keywords/weather-interference","display_name":"weather interference","score":0.6539999842643738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.675175666809082},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6589839458465576},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.43447279930114746},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3713953197002411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3281840980052948},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.17724773287773132},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.09583261609077454},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.24963/ijcai.2024/141","doi":"https://doi.org/10.24963/ijcai.2024/141","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2024/141","pdf_url":"https://www.ijcai.org/proceedings/2024/0141.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2401.03907","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.03907","pdf_url":"https://arxiv.org/pdf/2401.03907","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,"listed_in":[],"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.2401.03907","doi":"https://doi.org/10.48550/arxiv.2401.03907","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.03907","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2024/141","doi":"https://doi.org/10.24963/ijcai.2024/141","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2024/141","pdf_url":"https://www.ijcai.org/proceedings/2024/0141.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3291954615","display_name":null,"funder_award_id":"2023YJS019","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401023960.pdf","grobid_xml":"https://content.openalex.org/works/W4401023960.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W4382322597","https://openalex.org/W4388543919","https://openalex.org/W4390874155","https://openalex.org/W4390874213","https://openalex.org/W4393387578","https://openalex.org/W4401634204","https://openalex.org/W4408411785"],"related_works":["https://openalex.org/W7214008441","https://openalex.org/W7133490962","https://openalex.org/W7137954591","https://openalex.org/W7203823370","https://openalex.org/W4403364900","https://openalex.org/W4416400135","https://openalex.org/W7123872414","https://openalex.org/W7155581473","https://openalex.org/W4409762076","https://openalex.org/W4416932182"],"abstract_inverted_index":{"Multi-modal":[0],"3D":[1,59,168],"object":[2,60,169],"detectors":[3],"are":[4,49],"dedicated":[5],"to":[6,28,76,117,135],"exploring":[7],"secure":[8],"and":[9,32,47,55,126,158,184],"reliable":[10],"perception":[11],"systems":[12],"for":[13,51,88,105,122],"autonomous":[14],"driving":[15],"(AD).":[16],"Although":[17],"achieving":[18],"state-of-the-art":[19],"(SOTA)":[20],"performance":[21,175],"on":[22],"clean":[23],"benchmark":[24],"datasets,":[25],"they":[26],"tend":[27],"overlook":[29],"the":[30,39,53,85,107,119,138,156,164,182],"complexity":[31],"harsh":[33],"conditions":[34],"of":[35,41,57,160,166],"real-world":[36],"environments.":[37],"With":[38],"emergence":[40],"visual":[42],"foundation":[43],"models":[44],"(VFMs),":[45],"opportunities":[46],"challenges":[48],"presented":[50],"improving":[52],"robustness":[54,159],"generalization":[56,157],"multi-modal":[58,99,167],"detection":[61],"in":[62,176],"AD.":[63],"Therefore,":[64],"we":[65,101,131],"propose":[66],"RoboFusion,":[67],"a":[68],"robust":[69],"framework":[70],"that":[71],"leverages":[72],"VFMs":[73],"like":[74],"SAM":[75,87,95],"tackle":[77],"out-of-distribution":[78],"(OOD)":[79],"noise":[80,124,153],"scenarios.":[81],"We":[82,113],"first":[83],"adapt":[84],"original":[86],"AD":[89],"scenarios":[90],"named":[91],"SAM-AD.":[92],"To":[93],"align":[94],"or":[96],"SAM-AD":[97],"with":[98],"methods,":[100],"then":[102],"introduce":[103],"AD-FPN":[104],"upsampling":[106],"image":[108],"features":[109,143],"extracted":[110],"by":[111,154,181],"SAM.":[112],"employ":[114,132],"wavelet":[115],"decomposition":[116],"denoise":[118],"depth-guided":[120],"images":[121],"further":[123],"reduction":[125],"weather":[127],"interference.":[128],"At":[129],"last,":[130],"self-attention":[133],"mechanisms":[134],"adaptively":[136],"reweight":[137],"fused":[139],"features,":[140],"enhancing":[141,163],"informative":[142],"while":[144],"suppressing":[145],"excess":[146],"noise.":[147],"In":[148],"summary,":[149],"RoboFusion":[150,172],"significantly":[151],"reduces":[152],"leveraging":[155],"VFMs,":[161],"thereby":[162],"resilience":[165],"detection.":[170],"Consequently,":[171],"achieves":[173],"SOTA":[174],"noisy":[177],"scenarios,":[178],"as":[179],"demonstrated":[180],"KITTI-C":[183],"nuScenes-C":[185],"benchmarks.":[186],"Code":[187],"is":[188],"available":[189],"at":[190],"https://github.com/adept-thu/RoboFusion.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":21},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":15}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-07-27T00:00:00"}