{"id":"https://openalex.org/W7170183452","doi":"https://doi.org/10.48550/arxiv.2607.20238","title":"Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training","display_name":"Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training","publication_year":2026,"publication_date":"2026-07-22","ids":{"openalex":"https://openalex.org/W7170183452","doi":"https://doi.org/10.48550/arxiv.2607.20238"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.20238","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.20238","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.20238","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109597339","display_name":"Q L","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Qiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143467317","display_name":"Bin Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Bin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143465143","display_name":"Junjie Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Junjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090092559","display_name":"Qiangjuan Huang","orcid":"https://orcid.org/0000-0001-6630-3467"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Qiangjuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011401698","display_name":"Puhong Duan","orcid":"https://orcid.org/0000-0001-5066-4399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Puhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143484283","display_name":"Ke Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Ke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129959799","display_name":"X Kang (9851831)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Xudong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5143487250","display_name":"Shutao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Shutao","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":0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.24210000038146973,"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":0.24210000038146973,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.18019999563694,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.08370000123977661,"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/sampling","display_name":"Sampling (signal processing)","score":0.699999988079071},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6287999749183655},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.595300018787384},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5360000133514404},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5307999849319458},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5199000239372253},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.47870001196861267}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7193999886512756},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.699999988079071},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6287999749183655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6208000183105469},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.595300018787384},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5360000133514404},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5307999849319458},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.47870001196861267},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46950000524520874},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4641000032424927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4375999867916107},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3061000108718872},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2596000134944916},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.20238","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.20238","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.20238","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.20238","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6239389181137085,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visible-infrared":[0],"(VIS-IR)":[1],"alignment":[2,139],"is":[3,127,132],"a":[4,59,95,100,112],"key":[5],"pre-training":[6,57],"task":[7],"for":[8,161],"robust":[9],"multi-sensor":[10],"perception.":[11],"Most":[12],"existing":[13],"methods":[14],"use":[15],"uniform":[16],"patch-wise":[17],"contrastive":[18,91,144],"learning,":[19],"but":[20],"this":[21,52],"can":[22],"be":[23,178],"unreliable":[24],"in":[25],"VIS-IR":[26,56,152],"data":[27],"because":[28],"imaging-physics":[29],"differences":[30],"make":[31],"some":[32],"spatially":[33],"paired":[34],"regions":[35,122],"inherently":[36],"less":[37],"comparable,":[38],"and":[39,48,62,85,109,134,142,168,172],"aligning":[40],"them":[41,87],"with":[42,99,136],"equal":[43],"strength":[44],"hinders":[45],"representation":[46],"learning":[47,115],"downstream":[49],"transfer.":[50],"In":[51],"paper,":[53],"we":[54],"revisit":[55],"from":[58,81,105,120],"sampling":[60],"perspective":[61],"propose":[63],"Importance-Aware":[64],"Sampling":[65],"(IAS),":[66],"which":[67],"adjusts":[68],"training":[69],"emphasis":[70],"based":[71],"on":[72,150,180],"patch":[73,79,113],"reliability.":[74],"Specifically,":[75],"IAS":[76,131],"(i)":[77],"derives":[78],"weights":[80],"infrared":[82],"structural":[83],"cues":[84],"uses":[86],"to":[88,123],"reweight":[89],"the":[90,106],"objective;":[92],"(ii)":[93],"learns":[94],"soft":[96],"importance":[97],"mask":[98],"lightweight":[101],"sampler,":[102],"optionally":[103],"warm-started":[104],"hand-crafted":[107],"prior;":[108],"(iii)":[110],"employs":[111],"curriculum":[114],"strategy":[116],"that":[117,130],"gradually":[118],"expands":[119],"high-reliability":[121],"harder":[124],"patches.":[125],"It":[126],"worth":[128],"noting":[129],"plug-and-play":[133],"works":[135],"both":[137],"patch-/correlation-level":[138],"(e.g.,":[140,146],"UNIV-style)":[141],"image-level":[143],"baselines":[145],"ImageBind-style).":[147],"Extensive":[148],"experiments":[149],"multiple":[151],"benchmarks":[153],"demonstrate":[154],"consistent":[155],"improvements":[156],"over":[157],"strong":[158],"baselines,":[159],"including":[160],"IR":[162,165],"semantic":[163,170],"segmentation,":[164],"object":[166],"detection":[167],"VIS":[169],"segmentation":[171],"cross-modal":[173],"retrieval":[174],"task.":[175],"Code":[176],"will":[177],"released":[179],"https://github.com/KlayMa527/IAS.":[181]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-24T00:00:00"}