{"id":"https://openalex.org/W7077047813","doi":"https://doi.org/10.48550/arxiv.2507.20186","title":"SAMwave: Wavelet-Driven Feature Enrichment for Effective Adaptation of Segment Anything Model","display_name":"SAMwave: Wavelet-Driven Feature Enrichment for Effective Adaptation of Segment Anything Model","publication_year":2025,"publication_date":"2025-07-27","ids":{"openalex":"https://openalex.org/W7077047813","doi":"https://doi.org/10.48550/arxiv.2507.20186"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2507.20186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.20186","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.2507.20186","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yadav, Saurabh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yadav, Saurabh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gupta, Avi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gupta, Avi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Jerripothula, Koteswar Rao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jerripothula, Koteswar Rao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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":true,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.4334999918937683,"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"}},"topics":[{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.4334999918937683,"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/T13177","display_name":"Geological and Geophysical Studies","score":0.0406000018119812,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13067","display_name":"Geological Modeling and Analysis","score":0.031300000846385956,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7354000210762024},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6169999837875366},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.4812999963760376},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4731000065803528},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44369998574256897},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4336000084877014}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777400016784668},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7354000210762024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6790000200271606},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6169999837875366},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.4812999963760376},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4731000065803528},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44369998574256897},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.430400013923645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40790000557899475},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.34360000491142273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33980000019073486},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26109999418258667},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2507.20186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.20186","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.2507.20186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.20186","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,13],"emergence":[1],"of":[2,121,191],"large":[3],"foundation":[4,32],"models":[5,33],"has":[6],"propelled":[7],"significant":[8],"advances":[9],"in":[10,84],"various":[11],"domains.":[12],"Segment":[14],"Anything":[15],"Model":[16],"(SAM),":[17],"a":[18,95],"leading":[19],"model":[20],"for":[21,44,60,145,178,195],"image":[22],"segmentation,":[23],"exemplifies":[24],"these":[25,76,133],"advances,":[26],"outperforming":[27],"traditional":[28],"methods.":[29,163],"However,":[30,71],"such":[31],"often":[34],"suffer":[35],"from":[36,67,111],"performance":[37,166],"degradation":[38],"when":[39],"applied":[40],"to":[41,57,82,105,140],"complex":[42,127],"tasks":[43,61,155],"which":[45],"they":[46],"are":[47],"not":[48],"trained.":[49],"Existing":[50],"methods":[51],"typically":[52],"employ":[53],"adapter-based":[54],"fine-tuning":[55],"strategies":[56],"adapt":[58],"SAM":[59,172],"and":[62,97,173,176,181,189],"leverage":[63],"high-frequency":[64,109],"features":[65,110],"extracted":[66],"the":[68,102,171,186],"Fourier":[69],"domain.":[70],"Our":[72],"analysis":[73],"reveals":[74],"that":[75,100,157],"approaches":[77],"offer":[78],"limited":[79],"benefits":[80],"due":[81],"constraints":[83],"their":[85],"feature":[86],"extraction":[87],"techniques.":[88],"To":[89],"overcome":[90],"this,":[91,115],"we":[92,116],"propose":[93],"\\textbf{\\textit{SAMwave}},":[94],"novel":[96],"interpretable":[98],"approach":[99],"utilizes":[101],"wavelet":[103,128,134],"transform":[104],"extract":[106],"richer,":[107],"multi-scale":[108],"input":[112],"data.":[113],"Extending":[114],"introduce":[117],"complex-valued":[118,123,182],"adapters":[119],"capable":[120],"capturing":[122],"spatial-frequency":[124],"information":[125,142],"via":[126],"transforms.":[129],"By":[130],"adaptively":[131],"integrating":[132],"coefficients,":[135],"SAMwave":[136,158],"enables":[137],"SAM's":[138],"encoder":[139],"capture":[141],"more":[143],"relevant":[144],"dense":[146],"prediction.":[147],"Empirical":[148],"evaluations":[149],"on":[150],"four":[151],"challenging":[152],"low-level":[153],"vision":[154],"demonstrate":[156],"significantly":[159],"outperforms":[160],"existing":[161],"adaptation":[162],"This":[164],"superior":[165],"is":[167],"consistent":[168],"across":[169],"both":[170,179],"SAM2":[174],"backbones":[175],"holds":[177],"real":[180],"adapter":[183],"variants,":[184],"highlighting":[185],"efficiency,":[187],"flexibility,":[188],"interpretability":[190],"our":[192],"proposed":[193],"method":[194],"adapting":[196],"segment":[197],"anything":[198],"models.":[199]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}