{"id":"https://openalex.org/W4408355896","doi":"https://doi.org/10.1109/icassp49660.2025.10890464","title":"FreeSegDiff: Annotation-free Saliency Segmentation with Diffusion Models","display_name":"FreeSegDiff: Annotation-free Saliency Segmentation with Diffusion Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355896","doi":"https://doi.org/10.1109/icassp49660.2025.10890464"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102841916","display_name":"Chaofan Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chaofan Ma","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100971040","display_name":"Yuhuan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhuan Yang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100774574","display_name":"Chen Ju","orcid":"https://orcid.org/0000-0001-8472-7677"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Ju","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101796102","display_name":"Yue Shi","orcid":"https://orcid.org/0000-0003-4254-8149"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Shi","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342828","display_name":"Ya Zhang","orcid":"https://orcid.org/0000-0002-5390-9053"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100645705","display_name":"Yanfeng Wang","orcid":"https://orcid.org/0000-0002-3196-2347"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfeng Wang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102841916"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04390309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9839000105857849,"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":0.9839000105857849,"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/annotation","display_name":"Annotation","score":0.738012433052063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7060376405715942},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6828521490097046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5876741409301758},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5358361601829529},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.46604788303375244},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38294699788093567},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3500261902809143}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.738012433052063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060376405715942},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6828521490097046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5876741409301758},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5358361601829529},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.46604788303375244},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38294699788093567},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3500261902809143},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1920234547","https://openalex.org/W2002781701","https://openalex.org/W2039313011","https://openalex.org/W2047670868","https://openalex.org/W2121947440","https://openalex.org/W2150593711","https://openalex.org/W2161236525","https://openalex.org/W2254462240","https://openalex.org/W2294182682","https://openalex.org/W2740667773","https://openalex.org/W3035524453","https://openalex.org/W3155072588","https://openalex.org/W3159481202","https://openalex.org/W3167788848","https://openalex.org/W3173859428","https://openalex.org/W3212516020","https://openalex.org/W4213060883","https://openalex.org/W4221161778","https://openalex.org/W4221167012","https://openalex.org/W4312497550","https://openalex.org/W4312933868","https://openalex.org/W4312971576","https://openalex.org/W4313026212","https://openalex.org/W4313145515","https://openalex.org/W4313150877","https://openalex.org/W4313156423","https://openalex.org/W4313186194","https://openalex.org/W4386071643","https://openalex.org/W4386076368","https://openalex.org/W4400582175","https://openalex.org/W4411244723","https://openalex.org/W6739696289","https://openalex.org/W6768279175","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6791353385","https://openalex.org/W6795094127","https://openalex.org/W6795288823","https://openalex.org/W6796634059","https://openalex.org/W6800989748","https://openalex.org/W6802517928","https://openalex.org/W6809885388","https://openalex.org/W6810940779","https://openalex.org/W6838639034","https://openalex.org/W6845839425","https://openalex.org/W6846007759","https://openalex.org/W6846385215","https://openalex.org/W6855261814","https://openalex.org/W6856659049"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W4405124681","https://openalex.org/W1533177136","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Learning":[0],"from":[1],"a":[2,15,56,66,83,118],"large":[3],"corpus":[4],"of":[5,77,163],"data,":[6],"pre-trained":[7,43],"models":[8,21,45,64],"have":[9],"achieved":[10],"impressive":[11],"progress":[12],"nowadays.":[13],"As":[14],"popular":[16],"generative":[17,61],"pre-training":[18],"method,":[19],"diffusion":[20,44,70,146,165],"stand":[22],"out":[23],"by":[24],"capturing":[25],"both":[26],"low-level":[27],"visual":[28],"knowledge":[29],"and":[30,62,116,157],"high-level":[31],"semantic":[32],"relations.":[33],"In":[34,103,125],"this":[35],"paper,":[36],"we":[37,93,112,135],"propose":[38,117],"to":[39,69,108,122,130,140,145],"exploit":[40],"such":[41,50],"knowledgeable":[42],"for":[46,166],"mainstream":[47],"discriminative":[48,63],"tasks":[49],"as":[51],"annotation-free":[52,87,167],"saliency":[53,168],"segmentation.":[54,169],"However,":[55],"notable":[57],"structural":[58,133],"discrepancy":[59],"between":[60],"poses":[65],"significant":[67],"challenge":[68],"models\u2019":[71],"direct":[72],"application.":[73],"Furthermore,":[74],"the":[75,104,126,132,137,161],"absence":[76],"explicit":[78],"manually":[79],"labeled":[80],"data":[81,110],"is":[82],"substantial":[84],"barrier":[85],"in":[86],"settings.":[88],"To":[89],"tackle":[90],"these":[91],"issues,":[92],"introduce":[94],"FreeSegDiff,":[95],"one":[96],"novel":[97,119],"synthesis-exploitation":[98],"framework":[99],"containing":[100],"two-stage":[101],"strategies.":[102],"first":[105],"synthesis":[106],"stage,":[107,129],"alleviate":[109],"insufficiency,":[111],"synthesize":[113],"abundant":[114],"images,":[115],"training-free":[120],"DiffusionCut":[121],"produce":[123],"masks.":[124],"second":[127],"exploitation":[128],"bridge":[131],"gap,":[134],"employ":[136],"inversion":[138],"technique":[139],"convert":[141],"given":[142],"images":[143],"back":[144],"features.":[147],"These":[148],"features":[149],"seamlessly":[150],"integrate":[151],"with":[152],"downstream":[153],"architectures.":[154],"Extensive":[155],"experiments":[156],"ablation":[158],"studies":[159],"demonstrate":[160],"superiority":[162],"adapting":[164]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}