{"id":"https://openalex.org/W4414110893","doi":"https://doi.org/10.1109/tpami.2025.3600461","title":"Towards Real Zero-Shot Camouflaged Object Segmentation Without Camouflaged Annotations","display_name":"Towards Real Zero-Shot Camouflaged Object Segmentation Without Camouflaged Annotations","publication_year":2025,"publication_date":"2025-09-10","ids":{"openalex":"https://openalex.org/W4414110893","doi":"https://doi.org/10.1109/tpami.2025.3600461","pmid":"https://pubmed.ncbi.nlm.nih.gov/40928907"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3600461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3600461","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Cheng Lei","orcid":"https://orcid.org/0009-0007-0161-8688"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Lei","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China","University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0007-0161-8688","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jie Fan","orcid":"https://orcid.org/0009-0002-5731-6279"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Fan","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China","University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0002-5731-6279","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinran Li","orcid":"https://orcid.org/0009-0005-7442-437X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinran Li","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China","University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0005-7442-437X","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085828297","display_name":"Tian-Zhu Xiang","orcid":"https://orcid.org/0000-0002-3321-1993"},"institutions":[{"id":"https://openalex.org/I117222138","display_name":"Abu Dhabi University","ror":"https://ror.org/01r3kjq03","country_code":"AE","type":"education","lineage":["https://openalex.org/I117222138"]},{"id":"https://openalex.org/I3148377317","display_name":"Department of Space","ror":"https://ror.org/000kjq947","country_code":"IN","type":"government","lineage":["https://openalex.org/I3148377317"]}],"countries":["AE","IN"],"is_corresponding":false,"raw_author_name":"Tian-Zhu Xiang","raw_affiliation_strings":["Space42, Abu Dhabi, UAE","Space42, UAE"],"raw_orcid":"https://orcid.org/0000-0002-3321-1993","affiliations":[{"raw_affiliation_string":"Space42, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I117222138"]},{"raw_affiliation_string":"Space42, UAE","institution_ids":["https://openalex.org/I3148377317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359745","display_name":"Ao Li","orcid":"https://orcid.org/0000-0002-8866-2302"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ao Li","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China","University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-8866-2302","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034427070","display_name":"Ce Zhu","orcid":"https://orcid.org/0000-0001-7607-707X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ce Zhu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China","University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0001-7607-707X","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":null,"display_name":"Le Zhang","orcid":"https://orcid.org/0000-0002-6930-8674"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Le Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China","University of Electronic Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-6930-8674","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1769,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.92785554,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"47","issue":"12","first_page":"11990","last_page":"12004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9986000061035156,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9986000061035156,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9976000189781189,"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":0.9886000156402588,"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/segmentation","display_name":"Segmentation","score":0.6330999732017517},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5303999781608582},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4742000102996826},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.44679999351501465},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43140000104904175},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42899999022483826},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4041999876499176},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.36500000953674316},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.3422999978065491},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.33709999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876999974250793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7318999767303467},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6330999732017517},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5303999781608582},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4742000102996826},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45730000734329224},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.44679999351501465},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42899999022483826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4041999876499176},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C193125573","wikidata":"https://www.wikidata.org/wiki/Q7449065","display_name":"Semantic interpretation","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3255000114440918},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3086000084877014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.29899999499320984},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2964000105857849},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.2777000069618225},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.25609999895095825},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3600461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3600461","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40928907","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40928907","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1994922096","https://openalex.org/W2021088830","https://openalex.org/W2326050853","https://openalex.org/W2740667773","https://openalex.org/W2943545929","https://openalex.org/W2948300571","https://openalex.org/W2963529609","https://openalex.org/W2963868681","https://openalex.org/W2982247743","https://openalex.org/W2995936506","https://openalex.org/W2997286550","https://openalex.org/W3011305844","https://openalex.org/W3034684132","https://openalex.org/W3039479109","https://openalex.org/W3094502228","https://openalex.org/W3134992255","https://openalex.org/W3143107425","https://openalex.org/W3153675281","https://openalex.org/W3164098653","https://openalex.org/W3176828726","https://openalex.org/W3177004386","https://openalex.org/W3177087374","https://openalex.org/W3209732904","https://openalex.org/W4205460703","https://openalex.org/W4214561053","https://openalex.org/W4221151441","https://openalex.org/W4285601297","https://openalex.org/W4299652825","https://openalex.org/W4312232166","https://openalex.org/W4312258849","https://openalex.org/W4312446817","https://openalex.org/W4312651322","https://openalex.org/W4312880622","https://openalex.org/W4313151123","https://openalex.org/W4362602094","https://openalex.org/W4367663208","https://openalex.org/W4382450131","https://openalex.org/W4382465636","https://openalex.org/W4385764597","https://openalex.org/W4385809408","https://openalex.org/W4386065512","https://openalex.org/W4386065718","https://openalex.org/W4386075673","https://openalex.org/W4386076039","https://openalex.org/W4386076522","https://openalex.org/W4386265875","https://openalex.org/W4387185378","https://openalex.org/W4387968615","https://openalex.org/W4388574886","https://openalex.org/W4390190100","https://openalex.org/W4390871785","https://openalex.org/W4390874575","https://openalex.org/W4393159738","https://openalex.org/W4399923948","https://openalex.org/W4400721967","https://openalex.org/W4401024939","https://openalex.org/W4402660119","https://openalex.org/W4403791683","https://openalex.org/W4404612501","https://openalex.org/W4405056285","https://openalex.org/W4405519151","https://openalex.org/W4406457466","https://openalex.org/W4407870928"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2114275278","https://openalex.org/W1522196789","https://openalex.org/W1489511283","https://openalex.org/W2974914859","https://openalex.org/W2026565050","https://openalex.org/W2110244802","https://openalex.org/W2163728705","https://openalex.org/W949345935"],"abstract_inverted_index":{"Camouflaged":[0],"Object":[1],"Segmentation":[2],"(COS)":[3],"faces":[4],"significant":[5],"challenges":[6],"due":[7,24],"to":[8,25,196,229,282],"the":[9,26,31,57,111,176,194,231,272],"scarcity":[10],"of":[11,116,219,262,284],"annotated":[12],"data,":[13],"where":[14],"meticulous":[15],"pixel-level":[16],"annotation":[17],"is":[18],"both":[19,94,306],"labor-intensive":[20],"and":[21,64,96,123,161,181,247,266,298,308],"costly,":[22],"primarily":[23],"intricate":[27],"object-background":[28],"boundaries.":[29],"Addressing":[30],"core":[32],"question,":[33],"\"Can":[34],"COS":[35,69,117,257],"be":[36],"effectively":[37],"achieved":[38],"in":[39,86,255,295,305,315],"a":[40,66,106,124,142,155,162,226],"zero-shot":[41,68,135,256,307],"manner":[42],"without":[43],"manual":[44],"annotations":[45],"for":[46,61,78,137,151],"any":[47],"camouflaged":[48,62,90],"object?\",":[49],"we":[50,104,192,224,276],"propose":[51],"an":[52,278],"affirmative":[53],"solution.":[54],"We":[55,140],"examine":[56],"learned":[58],"attention":[59,88,98,121],"patterns":[60,122],"objects":[63],"introduce":[65,225],"robust":[67],"framework.":[70],"Our":[71,242],"findings":[72],"reveal":[73],"that":[74,108,283],"while":[75,118,175,239],"transformer":[76],"models":[77],"salient":[79],"object":[80,91],"segmentation":[81,92,317],"(SOS)":[82],"prioritize":[83],"global":[84,95,120,180],"features":[85,211],"their":[87],"mechanisms,":[89],"exhibits":[93],"local":[97,113,173],"biases.":[99],"Based":[100],"on":[101,201,264,268],"these":[102],"findings,":[103],"design":[105],"framework":[107,243],"adapts":[109],"with":[110,208,258],"inherent":[112],"pattern":[114],"bias":[115],"incorporating":[119],"broad":[125],"semantic":[126,182,190,221],"feature":[127],"space":[128],"derived":[129],"from":[130,184],"SOS.":[131],"This":[132,214],"enables":[133,216],"efficient":[134],"transfer":[136],"COS.":[138],"Specifically,":[139],"incorporate":[141],"Masked":[143],"Image":[144],"Modeling":[145],"(MIM)":[146],"based":[147],"image":[148],"encoder":[149,170],"optimized":[150],"Parameter-Efficient":[152],"Fine-Tuning":[153],"(PEFT),":[154],"Multimodal":[156],"Large":[157],"Language":[158],"Model":[159],"(M-LLM),":[160],"Multi-scale":[163],"Fine-grained":[164],"Alignment":[165],"(MFA)":[166],"mechanism.":[167],"The":[168],"MIM":[169],"captures":[171],"essential":[172],"features,":[174],"PEFT":[177],"module":[178],"learns":[179],"representations":[183],"SOS":[185],"datasets.":[186],"To":[187],"further":[188],"enhance":[189],"granularity,":[191],"leverage":[193],"M-LLM":[195,232,273],"generate":[197],"caption":[198],"embeddings":[199],"conditioned":[200],"visual":[202,210],"cues,":[203],"which":[204],"are":[205],"meticulously":[206],"aligned":[207],"multi-scale":[209],"via":[212],"MFA.":[213],"alignment":[215],"precise":[217],"interpretation":[218],"complex":[220],"contexts.":[222],"Moreover,":[223],"learnable":[227],"codebook":[228],"represent":[230],"during":[233,274],"inference,":[234,275],"significantly":[235],"reducing":[236],"computational":[237],"demands":[238],"maintaining":[240],"performance.":[241],"demonstrates":[244],"its":[245,313],"versatility":[246],"efficacy":[248],"through":[249],"rigorous":[250],"experimentation,":[251],"achieving":[252],"state-of-the-art":[253],"performance":[254],"$F_{\\beta":[259],"}^{w}$F\u03b2w":[260],"scores":[261],"72.9%":[263],"CAMO":[265],"71.7%":[267],"COD10K.":[269],"By":[270],"removing":[271],"achieve":[277],"inference":[279],"speed":[280],"comparable":[281],"traditional":[285],"end-to-end":[286],"models,":[287],"reaching":[288],"18.1":[289],"FPS.":[290],"Additionally,":[291],"our":[292],"method":[293],"excels":[294],"polyp":[296],"segmentation,":[297,301],"underwater":[299],"scene":[300],"outperforming":[302],"challenging":[303],"baselines":[304],"supervised":[309],"settings,":[310],"thereby":[311],"implying":[312],"potentiality":[314],"various":[316],"tasks.":[318]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}