{"id":"https://openalex.org/W7159064538","doi":"https://doi.org/10.48550/arxiv.2604.26806","title":"ViCrop-Det: Spatial Attention Entropy Guided Cropping for Training-Free Small-Object Detection","display_name":"ViCrop-Det: Spatial Attention Entropy Guided Cropping for Training-Free Small-Object Detection","publication_year":2026,"publication_date":"2026-04-29","ids":{"openalex":"https://openalex.org/W7159064538","doi":"https://doi.org/10.48550/arxiv.2604.26806"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.26806","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26806","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.2604.26806","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134892542","display_name":"Hui Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101461241","display_name":"Hongze Li","orcid":"https://orcid.org/0000-0002-3985-6805"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hongze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134885955","display_name":"Wei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134919969","display_name":"Xiaojin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiaojin","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":0.8677999973297119,"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":0.8677999973297119,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.05000000074505806,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.027799999341368675,"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/entropy","display_name":"Entropy (arrow of time)","score":0.5699999928474426},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5396999716758728},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4986000061035156},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4255000054836273},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.40549999475479126},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.3840000033378601},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.3328999876976013},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.3140000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6840000152587891},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5699999928474426},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5069000124931335},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4986000061035156},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4255000054836273},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.3328999876976013},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3325999975204468},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C2777016058","wikidata":"https://www.wikidata.org/wiki/Q7574061","display_name":"Spatial distribution","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.296999990940094},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C158709400","wikidata":"https://www.wikidata.org/wiki/Q3578586","display_name":"Spatial ecology","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C106752470","wikidata":"https://www.wikidata.org/wiki/Q1364826","display_name":"Joint entropy","level":3,"score":0.2596000134944916},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.26806","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26806","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.2604.26806","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26806","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":[{"id":"https://metadata.un.org/sdg/17","score":0.4161161184310913,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0],"architectures":[1],"have":[2],"established":[3],"a":[4,29,63,114,177,214],"dominant":[5],"paradigm":[6],"in":[7,22,47,81],"global":[8,31,198],"semantic":[9],"perception;":[10],"however,":[11],"they":[12],"remain":[13],"fundamentally":[14],"constrained":[15],"by":[16,52,75],"the":[17,26,76,86,107,132,197],"profound":[18],"spatial":[19,70,105,111,133,144,199],"heterogeneity":[20],"inherent":[21],"natural":[23],"images.":[24],"Specifically,":[25],"imposition":[27],"of":[28,36,78],"uniform":[30,210],"receptive":[32],"field":[33],"across":[34],"regions":[35,120],"varying":[37],"information":[38],"density":[39],"inevitably":[40],"leads":[41],"to":[42,101,119,171],"local":[43,104],"feature":[44],"degradation,":[45],"particularly":[46],"dense":[48],"conflict":[49],"zones":[50],"populated":[51],"microscopic":[53],"targets.":[54],"To":[55],"address":[56],"this":[57],"mechanistic":[58],"limitation,":[59],"we":[60],"propose":[61],"ViCrop-Det,":[62],"training-free":[64],"inference":[65],"framework":[66,108],"that":[67,161],"introduces":[68],"adaptive":[69,205],"trust":[71,134],"region":[72,135],"shrinkage.":[73],"Inspired":[74],"use":[77],"attention":[79],"entropy":[80],"anomaly":[82],"segmentation,":[83],"ViCrop-Det":[84,141,162],"leverages":[85],"detection":[87],"decoder's":[88],"cross-attention":[89],"distribution":[90],"as":[91],"an":[92],"endogenous":[93],"probe.":[94],"By":[95,130],"utilizing":[96],"Spatial":[97],"Attention":[98],"Entropy":[99],"(SAE)":[100],"heuristically":[102],"evaluate":[103],"ambiguity,":[106],"executes":[109],"dynamic":[110],"routing,":[112],"allocating":[113],"fixed":[115],"computational":[116],"budget":[117],"exclusively":[118],"exhibiting":[121],"both":[122],"high":[123,127],"target":[124],"saliency":[125],"and":[126,136,146,158,173],"cognitive":[128],"uncertainty.":[129],"shrinking":[131],"injecting":[137],"high-frequency":[138],"localized":[139],"observations,":[140],"actively":[142],"resolves":[143],"ambiguity":[145],"recovers":[147],"fine-grained":[148],"features":[149],"without":[150,195],"requiring":[151],"architectural":[152],"modifications.":[153],"Extensive":[154],"evaluations":[155],"on":[156],"VisDrone":[157],"DOTA-v1.5":[159],"demonstrate":[160],"yields":[163],"competitive":[164],"performance":[165],"enhancements,":[166],"consistently":[167],"adding":[168],"+1-3":[169],"mAP@50":[170],"RT-DETR-R50":[172],"Deformable":[174],"DETR":[175],"with":[176],"marginal":[178],"20-23\\%":[179],"latency":[180],"overhead.":[181],"On":[182],"MS":[183],"COCO,":[184],"$AP_{S}$":[185],"improves":[186],"while":[187],"$AP_{M}/AP_{L}$":[188],"remains":[189],"stable,":[190],"indicating":[191],"precise":[192],"fine-scale":[193],"refinement":[194],"compromising":[196],"prior.":[200],"Under":[201],"compute-matched":[202],"settings,":[203],"our":[204],"routing":[206],"strategy":[207],"comprehensively":[208],"surpasses":[209],"slicing":[211],"baselines,":[212],"achieving":[213],"highly":[215],"optimized":[216],"accuracy-speed":[217],"trade-off.":[218]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-01T00:00:00"}