{"id":"https://openalex.org/W4417136708","doi":"https://doi.org/10.48550/arxiv.2508.03060","title":"CHARM: Collaborative Harmonization across Arbitrary Modalities for Modality-agnostic Semantic Segmentation","display_name":"CHARM: Collaborative Harmonization across Arbitrary Modalities for Modality-agnostic Semantic Segmentation","publication_year":2025,"publication_date":"2025-08-05","ids":{"openalex":"https://openalex.org/W4417136708","doi":"https://doi.org/10.48550/arxiv.2508.03060"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2508.03060","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.03060","pdf_url":"https://arxiv.org/pdf/2508.03060","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,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.03060","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032066259","display_name":"Lekang Wen","orcid":"https://orcid.org/0009-0000-6222-4243","observed_orcids":["https://orcid.org/0009-0000-6222-4243"]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210118728","display_name":"State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing","ror":"https://ror.org/02bpap860","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118728"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen, Lekang","raw_affiliation_strings":["State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing , Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing , Wuhan University","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210118728"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Zhong Xiao","orcid":"https://orcid.org/0000-0001-9615-4749","observed_orcids":["https://orcid.org/0000-0001-9615-4749","https://orcid.org/0009-0003-7045-5537"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Jing","raw_affiliation_strings":["School of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133619771","display_name":"Liang Liao","orcid":"https://orcid.org/0000-0002-2238-2420","observed_orcids":["https://orcid.org/0000-0002-2238-2420","https://orcid.org/0009-0009-0059-4463"]},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liao, Liang","raw_affiliation_strings":["Hangzhou Institute of Technology , Xidian University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Institute of Technology , Xidian University","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427076","display_name":"Jiajun Chen","orcid":"https://orcid.org/0000-0001-5618-3932","observed_orcids":["https://orcid.org/0000-0001-5618-3932"]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210118728","display_name":"State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing","ror":"https://ror.org/02bpap860","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118728"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Jiajun","raw_affiliation_strings":["State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing , Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing , Wuhan University","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210118728"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wang, Mi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210118728","display_name":"State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing","ror":"https://ror.org/02bpap860","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210118728"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Mi","raw_affiliation_strings":["State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing , Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing , Wuhan University","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210118728"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.7163000106811523,"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":0.7163000106811523,"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":0.13040000200271606,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.13019999861717224,"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/cross-modal-alignment","display_name":"cross-modal alignment","score":0.43700000643730164},{"id":"https://openalex.org/keywords/cross-modal-interaction","display_name":"cross-modal interaction","score":0.5720000267028809},{"id":"https://openalex.org/keywords/collaborative-learning","display_name":"cooperative learning","score":0.6259999871253967}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7602999806404114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5975000262260437},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5924999713897705},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.565500020980835},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.5630000233650208},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46209999918937683},{"id":"https://openalex.org/C2779962950","wikidata":"https://www.wikidata.org/wiki/Q5659376","display_name":"Harmonization","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4262999892234802},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33320000767707825},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C60115397","wikidata":"https://www.wikidata.org/wiki/Q5188732","display_name":"Crossmodal","level":4,"score":0.32359999418258667},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2508.03060","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.03060","pdf_url":"https://arxiv.org/pdf/2508.03060","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,"listed_in":[],"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":"pmh:oai:ojs.aaai.org:article/38033","doi":null,"is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38033","pdf_url":null,"source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2508.03060","doi":"https://doi.org/10.48550/arxiv.2508.03060","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.03060","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2508.03060","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.03060","pdf_url":"https://arxiv.org/pdf/2508.03060","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417136708.pdf","grobid_xml":"https://content.openalex.org/works/W4417136708.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W4404988359","https://openalex.org/W4405749485","https://openalex.org/W4415539405"],"related_works":["https://openalex.org/W4405102069","https://openalex.org/W7150773500","https://openalex.org/W4416073398","https://openalex.org/W4405749485","https://openalex.org/W7222756698","https://openalex.org/W4403889639","https://openalex.org/W4386065698","https://openalex.org/W7147697631","https://openalex.org/W4404988359","https://openalex.org/W7168351603"],"abstract_inverted_index":{"Modality-agnostic":[0],"Semantic":[1],"Segmentation":[2],"(MaSS)":[3],"aims":[4],"to":[5,24,57,91,149],"achieve":[6,25,42],"robust":[7],"scene":[8],"understanding":[9],"across":[10,122],"arbitrary":[11],"combinations":[12],"of":[13,33],"input":[14],"modality.":[15],"Existing":[16],"methods":[17],"typically":[18],"rely":[19],"on":[20,137],"explicit":[21],"feature":[22],"alignment":[23,75],"modal":[26],"homogenization,":[27,47],"which":[28],"dilutes":[29],"the":[30,132,138,144],"distinctive":[31],"strengths":[32],"each":[34,89],"modality":[35],"and":[36,86,112,125],"destroys":[37],"their":[38],"inherent":[39],"complementarity.":[40],"To":[41],"cooperative":[43],"harmonization":[44],"rather":[45],"than":[46],"we":[48],"propose":[49],"CHARM,":[50],"a":[51],"novel":[52],"complementary":[53,109],"learning":[54,111],"framework":[55],"designed":[56],"implicitly":[58],"align":[59],"content":[60],"while":[61],"preserving":[62],"modality-specific":[63,119],"advantages":[64],"through":[65,76],"two":[66],"components:":[67],"(1)":[68],"Mutual":[69],"Perception":[70],"Unit":[71],"(MPU),":[72],"enabling":[73,151],"implicit":[74],"window-based":[77],"cross-modal":[78,152],"interaction,":[79],"where":[80],"modalities":[81],"serve":[82],"as":[83],"both":[84],"queries":[85],"contexts":[87],"for":[88,108,117,154],"other":[90],"discover":[92],"modality-interactive":[93],"correspondences;":[94],"(2)":[95],"A":[96],"dual-path":[97],"optimization":[98],"strategy":[99],"that":[100,128],"decouples":[101],"training":[102],"into":[103],"Collaborative":[104],"Learning":[105],"Strategy":[106,115],"(CoL)":[107],"fusion":[110],"Individual":[113],"Enhancement":[114],"(InE)":[116],"protected":[118],"optimization.":[120],"Experiments":[121],"multiple":[123],"datasets":[124],"backbones":[126],"indicate":[127],"CHARM":[129],"consistently":[130],"outperform":[131],"baselines,":[133],"with":[134],"significant":[135],"increment":[136],"fragile":[139],"modalities.":[140],"This":[141],"work":[142],"shifts":[143],"focus":[145],"from":[146],"model":[147],"homogenization":[148],"harmonization,":[150],"complementarity":[153],"true":[155],"harmony":[156],"in":[157],"diversity.":[158]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}