{"id":"https://openalex.org/W7160888172","doi":"https://doi.org/10.48550/arxiv.2605.09859","title":"Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval","display_name":"Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160888172","doi":"https://doi.org/10.48550/arxiv.2605.09859"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.09859","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09859","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.09859","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135950421","display_name":"Shijie Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135954536","display_name":"Yadan Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Yadan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135916282","display_name":"Zijian Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zijian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135921632","display_name":"Xin Yu","orcid":"https://orcid.org/0000-0001-7431-7383"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136000230","display_name":"Zi Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Zi","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/T11448","display_name":"Face recognition and analysis","score":0.7896000146865845,"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/T11448","display_name":"Face recognition and analysis","score":0.7896000146865845,"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":0.055399999022483826,"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"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.049400001764297485,"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/discriminative-model","display_name":"Discriminative model","score":0.682699978351593},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6679999828338623},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5665000081062317},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.560699999332428},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5503000020980835},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5048999786376953},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4521999955177307},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4431000053882599},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.436599999666214},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.43380001187324524}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.725600004196167},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.682699978351593},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6679999828338623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6111999750137329},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5665000081062317},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.560699999332428},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5503000020980835},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4521999955177307},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4431000053882599},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29600000381469727},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.09859","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09859","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.09859","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.09859","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7816492915153503,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-grained":[0],"image":[1],"retrieval":[2,24,44,75,169],"(FGIR)":[3],"typically":[4],"relies":[5],"on":[6,46,83,189],"supervision":[7,21],"from":[8,66,137],"seen":[9,30,103],"categories":[10,31],"to":[11,148,152,178],"learn":[12],"discriminative":[13],"embeddings":[14,170],"for":[15],"retrieving":[16],"unseen":[17,47,179],"categories.":[18,48,180],"However,":[19],"such":[20],"often":[22],"biases":[23],"models":[25],"toward":[26,69],"the":[27,34,63,87,90,126,130,133,138,149],"semantics":[28],"of":[29,129,141],"rather":[32],"than":[33],"underlying":[35],"appearance":[36,70,122,173],"characteristics":[37],"that":[38,61,156,167,183],"generalize":[39],"across":[40],"categories,":[41],"thereby":[42,175],"limiting":[43],"performance":[45,188],"To":[49],"tackle":[50],"this,":[51],"we":[52],"propose":[53],"GAPan,":[54],"a":[55,97,108,163],"Generative":[56],"Appearance":[57],"Prior":[58],"alignment":[59,165],"network":[60],"reformulates":[62],"learning":[64],"objective":[65,166],"category":[67,104],"prediction":[68],"modeling.":[71],"Technically,":[72],"GAPan":[73,185],"treats":[74],"features":[76,95],"with":[77,171],"an":[78],"invertible":[79,127],"density":[80,99],"model":[81],"based":[82],"normalizing":[84],"flows.":[85,131],"In":[86,132],"forward":[88],"direction,":[89,135],"flow":[91],"maps":[92],"all":[93],"instance":[94],"into":[96],"latent":[98],"space,":[100],"where":[101],"each":[102],"is":[105],"modeled":[106],"by":[107,124],"class-conditional":[109],"Gaussian":[110],"prior":[111],"and":[112,193],"optimized":[113],"via":[114],"exact":[115],"likelihood":[116],"estimation.":[117],"This":[118],"formulation":[119],"preserves":[120],"richer":[121],"details":[123],"leveraging":[125],"property":[128],"reverse":[134],"samples":[136],"high-density":[139],"regions":[140],"these":[142],"learned":[143],"priors":[144],"are":[145],"mapped":[146],"back":[147],"feature":[150],"space":[151],"produce":[153],"appearance-aware":[154],"anchors":[155,161],"reflect":[157],"intra-category":[158],"variation.":[159],"These":[160],"supervise":[162],"prior-driven":[164],"aligns":[168],"category-specific":[172],"distributions,":[174],"improving":[176],"generalization":[177],"Evaluations":[181],"demonstrate":[182],"our":[184],"achieves":[186],"state-of-the-art":[187],"both":[190],"widely-used":[191],"fine-":[192],"coarse-grained":[194],"benchmarks.":[195]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-13T00:00:00"}