{"id":"https://openalex.org/W4399357914","doi":"https://doi.org/10.48550/arxiv.2406.00632","title":"Diff-Mosaic: Augmenting Realistic Representations in Infrared Small Target Detection via Diffusion Prior","display_name":"Diff-Mosaic: Augmenting Realistic Representations in Infrared Small Target Detection via Diffusion Prior","publication_year":2024,"publication_date":"2024-06-02","ids":{"openalex":"https://openalex.org/W4399357914","doi":"https://doi.org/10.48550/arxiv.2406.00632"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.00632","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.00632","pdf_url":"https://arxiv.org/pdf/2406.00632","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.00632","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039893934","display_name":"Yukai Shi","orcid":"https://orcid.org/0000-0002-9413-6528"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Yukai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100762393","display_name":"Yupei Lin","orcid":"https://orcid.org/0000-0001-6032-7898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Yupei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041227759","display_name":"Pengxu Wei","orcid":"https://orcid.org/0000-0002-2190-0767"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Pengxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008705798","display_name":"Xiaoyu Xian","orcid":"https://orcid.org/0009-0009-1851-6551"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xian, Xiaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052027147","display_name":"Tianshui Chen","orcid":"https://orcid.org/0000-0002-5848-5624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Tianshui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412937","display_name":"Liang Lin","orcid":"https://orcid.org/0000-0003-2248-3755"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Liang","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":true,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9994999766349792,"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/T11856","display_name":"Thermography and Photoacoustic Techniques","score":0.9577000141143799,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"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/T14158","display_name":"Optical Systems and Laser Technology","score":0.9490000009536743,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mosaic","display_name":"Mosaic","score":0.8567301630973816},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.633895993232727},{"id":"https://openalex.org/keywords/infrared","display_name":"Infrared","score":0.5778520107269287},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.422426700592041},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37614232301712036},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3441781997680664},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.17325255274772644},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.15780389308929443},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.12021934986114502},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.053680628538131714}],"concepts":[{"id":"https://openalex.org/C110739175","wikidata":"https://www.wikidata.org/wiki/Q133067","display_name":"Mosaic","level":2,"score":0.8567301630973816},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.633895993232727},{"id":"https://openalex.org/C158355884","wikidata":"https://www.wikidata.org/wiki/Q11388","display_name":"Infrared","level":2,"score":0.5778520107269287},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.422426700592041},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37614232301712036},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3441781997680664},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.17325255274772644},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.15780389308929443},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12021934986114502},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.053680628538131714},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.00632","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.00632","pdf_url":"https://arxiv.org/pdf/2406.00632","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.00632","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.00632","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":"pmh:oai:arXiv.org:2406.00632","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.00632","pdf_url":"https://arxiv.org/pdf/2406.00632","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399357914.pdf","grobid_xml":"https://content.openalex.org/works/W4399357914.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2493552207","https://openalex.org/W2397874377","https://openalex.org/W4249026204","https://openalex.org/W2027673787","https://openalex.org/W2327982655","https://openalex.org/W428377179","https://openalex.org/W1483215156","https://openalex.org/W4252212339","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Recently,":[0],"researchers":[1,44],"have":[2,123,233],"proposed":[3],"various":[4],"deep":[5,30],"learning":[6,31],"methods":[7,63,78,168],"to":[8,22,84,134,215],"accurately":[9],"detect":[10],"infrared":[11,27,42],"targets":[12],"with":[13,33,95],"the":[14,23,41,73,109,152,159,199,219,224,229,240,243],"characteristics":[15],"of":[16,26,71,92,132,161,165,176,228,242],"indistinct":[17],"shape":[18],"and":[19,81,137,163,191,226],"texture.":[20],"Due":[21],"limited":[24,106],"variety":[25],"datasets,":[28],"training":[29],"models":[32,122],"good":[34],"generalization":[35],"poses":[36],"a":[37,105,124,146],"challenge.":[38],"To":[39],"augment":[40],"dataset,":[43],"employ":[45],"data":[46,147,166],"augmentation":[47,148,167],"techniques,":[48],"which":[49,187],"often":[50],"involve":[51],"generating":[52],"new":[53],"images":[54,57,74,133,194,217],"by":[55,76,195],"combining":[56],"from":[58,100],"different":[59],"datasets.":[60],"However,":[61],"these":[62],"are":[64,82],"lacking":[65],"in":[66,218],"two":[67,177],"respects.":[68],"In":[69,90,140,198],"terms":[70,91],"realism,":[72],"generated":[75],"mixup-based":[77],"lack":[79],"realism":[80,164,227],"difficult":[83],"effectively":[85,157],"simulate":[86],"complex":[87],"real-world":[88,96,130,220],"scenarios.":[89],"diversity,":[93],"compared":[94],"scenes,":[97],"borrowing":[98],"knowledge":[99],"another":[101],"dataset":[102],"inherently":[103],"has":[104],"diversity.":[107],"Currently,":[108],"diffusion":[110,121,153,170,213],"model":[111,156,216],"stands":[112],"out":[113],"as":[114],"an":[115,182,204],"innovative":[116],"generative":[117,126],"approach.":[118],"Large-scale":[119],"trained":[120],"strong":[125],"prior":[127],"that":[128,235],"enables":[129],"modeling":[131],"generate":[135],"diverse":[136],"realistic":[138,192],"images.":[139,230],"this":[141],"paper,":[142],"we":[143,180,202],"propose":[144,203],"Diff-Mosaic,":[145],"method":[149,174],"based":[150],"on":[151],"model.":[154],"This":[155,210],"alleviates":[158],"challenge":[160],"diversity":[162,225],"via":[169],"prior.":[171],"Specifically,":[172],"our":[173,236],"consists":[175],"stages.":[178],"Firstly,":[179],"introduce":[181],"enhancement":[183,206],"network":[184],"called":[185],"Pixel-Prior,":[186],"generates":[188],"highly":[189],"coordinated":[190],"Mosaic":[193],"harmonizing":[196],"pixels.":[197],"second":[200],"stage,":[201],"image":[205],"strategy":[207,211],"named":[208],"Diff-Prior.":[209],"utilizes":[212],"priors":[214],"scene,":[221],"further":[222],"enhancing":[223],"Extensive":[231],"experiments":[232],"demonstrated":[234],"approach":[237],"significantly":[238],"improves":[239],"performance":[241],"detection":[244],"network.":[245],"The":[246],"code":[247],"is":[248],"available":[249],"at":[250],"https://github.com/YupeiLin2388/Diff-Mosaic":[251]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2024-06-06T00:00:00"}