{"id":"https://openalex.org/W7155370961","doi":"https://doi.org/10.48550/arxiv.2604.20358","title":"ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval","display_name":"ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7155370961","doi":"https://doi.org/10.48550/arxiv.2604.20358"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.20358","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20358","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.20358","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134457567","display_name":"Zixu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zixu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134442302","display_name":"Yupeng Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Yupeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134454314","display_name":"Zhiwei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134369590","display_name":"Mingyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Mingyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134447484","display_name":"Zhiheng Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Zhiheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134403249","display_name":"Liqiang Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie, Liqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.44909998774528503,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.44909998774528503,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.4406000077724457,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.01640000008046627,"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/robustness","display_name":"Robustness (evolution)","score":0.7545999884605408},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5931000113487244},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5432999730110168},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5412999987602234},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.47679999470710754},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4595000147819519},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45899999141693115},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4194999933242798}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7545999884605408},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.734499990940094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6176000237464905},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5931000113487244},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5432999730110168},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5412999987602234},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47679999470710754},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45899999141693115},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.32170000672340393},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3174000084400177},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2793999910354614},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.20358","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20358","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.20358","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20358","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"Composed":[1],"Image":[2],"Retrieval":[3],"(CIR)":[4],"task":[5],"provides":[6],"a":[7,12,65,114,133,149],"flexible":[8],"retrieval":[9],"paradigm":[10],"via":[11],"reference":[13,51],"image":[14],"and":[15,24,52,85,104,130,192,207],"modification":[16,60],"text,":[17],"but":[18,58],"it":[19,76],"heavily":[20],"relies":[21],"on":[22,188],"expensive":[23],"error-prone":[25],"triplet":[26],"annotations.":[27,40],"This":[28],"paper":[29],"systematically":[30],"investigates":[31],"the":[32,50,59,78,93,162,173,205],"Noisy":[33],"Triplet":[34],"Correspondence":[35,71],"(NTC)":[36],"problem":[37],"introduced":[38],"by":[39],"We":[41,83],"find":[42],"that":[43,195],"NTC":[44,94],"noise,":[45],"particularly":[46],"``hard":[47],"noise''":[48],"(i.e.,":[49],"target":[53],"images":[54],"are":[55],"highly":[56],"similar":[57],"text":[61],"is":[62],"incorrect),":[63],"poses":[64],"unique":[66],"challenge":[67],"to":[68,136],"existing":[69],"Noise":[70],"Learning":[72],"(NCL)":[73],"methods":[74],"because":[75],"breaks":[77],"traditional":[79],"``small":[80],"loss":[81],"hypothesis''.":[82],"identify":[84],"elucidate":[86],"three":[87],"key,":[88],"yet":[89],"overlooked,":[90],"challenges":[91],"in":[92,161],"task,":[95],"namely":[96],"(C1)":[97],"Modality":[98],"Suppression,":[99],"(C2)":[100],"Negative":[101,144],"Anchor":[102],"Deficiency,":[103],"(C3)":[105],"Unlearning":[106,184],"Backlash.":[107,185],"To":[108],"address":[109],"these":[110],"challenges,":[111],"we":[112,122,142,166],"propose":[113,124],"Cone-based":[115],"robuSt":[116],"noisE-unlearning":[117],"comPositional":[118],"network":[119],"(ConeSep).":[120],"Specifically,":[121],"first":[123],"Geometric":[125],"Fidelity":[126],"Quantization,":[127],"theoretically":[128],"establishing":[129],"practically":[131],"estimating":[132],"noise":[134],"boundary":[135],"precisely":[137],"locate":[138],"noisy":[139,174],"correspondence.":[140],"Next,":[141],"introduce":[143],"Boundary":[145],"Learning,":[146],"which":[147,171,202],"learns":[148],"``diagonal":[150],"negative":[151],"combination''":[152],"for":[153],"each":[154],"query":[155],"as":[156,177],"its":[157],"explicit":[158],"semantic":[159],"opposite-anchor":[160],"embedding":[163],"space.":[164],"Finally,":[165],"design":[167],"Boundary-based":[168],"Targeted":[169],"Unlearning,":[170],"models":[172],"correction":[175],"process":[176],"an":[178],"optimal":[179],"transport":[180],"problem,":[181],"elegantly":[182],"avoiding":[183],"Extensive":[186],"experiments":[187],"benchmark":[189],"datasets":[190],"(FashionIQ":[191],"CIRR)":[193],"demonstrate":[194],"ConeSep":[196],"significantly":[197],"outperforms":[198],"current":[199],"state-of-the-art":[200],"methods,":[201],"fully":[203],"demonstrates":[204],"effectiveness":[206],"robustness":[208],"of":[209],"our":[210],"method.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-24T00:00:00"}