{"id":"https://openalex.org/W4414165968","doi":"https://doi.org/10.1109/tmm.2025.3607734","title":"Potential of Diffusion-Generated Data on Salient Object Detection","display_name":"Potential of Diffusion-Generated Data on Salient Object Detection","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414165968","doi":"https://doi.org/10.1109/tmm.2025.3607734"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2025.3607734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3607734","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-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":null,"display_name":"Xiangquan Liu","orcid":"https://orcid.org/0009-0003-9586-7618"},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangquan Liu","raw_affiliation_strings":["Computer School, Beijing Information Science and Technology University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-9586-7618","affiliations":[{"raw_affiliation_string":"Computer School, Beijing Information Science and Technology University, Beijing, China","institution_ids":["https://openalex.org/I78675632"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102611212","display_name":"Xianlong Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianlong Luo","raw_affiliation_strings":["Computer School, Beijing Information Science and Technology University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-9607-232X","affiliations":[{"raw_affiliation_string":"Computer School, Beijing Information Science and Technology University, Beijing, China","institution_ids":["https://openalex.org/I78675632"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ying Ye","orcid":"https://orcid.org/0009-0004-2654-0395"},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Ye","raw_affiliation_strings":["Computer School, Beijing Information Science and Technology University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-2654-0395","affiliations":[{"raw_affiliation_string":"Computer School, Beijing Information Science and Technology University, Beijing, China","institution_ids":["https://openalex.org/I78675632"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668774","display_name":"Xiaoming Huang","orcid":"https://orcid.org/0000-0003-4254-2820"},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Huang","raw_affiliation_strings":["Computer School, Beijing Information Science and Technology University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4254-2820","affiliations":[{"raw_affiliation_string":"Computer School, Beijing Information Science and Technology University, Beijing, China","institution_ids":["https://openalex.org/I78675632"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78675632"],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74918686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"27","issue":null,"first_page":"8449","last_page":"8461"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9261000156402588,"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":0.9261000156402588,"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":0.6541000008583069},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.603600025177002},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5627999901771545},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5461999773979187},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5397999882698059},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5095000267028809},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4837000072002411},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.45399999618530273},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.45239999890327454},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44929999113082886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8633999824523926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6894000172615051},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6541000008583069},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.603600025177002},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5627999901771545},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5461999773979187},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5397999882698059},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5095000267028809},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4837000072002411},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.45399999618530273},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40450000762939453},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.3346000015735626},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.3075000047683716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3043999969959259},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2773999869823456},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.2702000141143799},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2025.3607734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2025.3607734","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1894057436","https://openalex.org/W1942214758","https://openalex.org/W2002781701","https://openalex.org/W2037227137","https://openalex.org/W2039313011","https://openalex.org/W2086866337","https://openalex.org/W2097878628","https://openalex.org/W2157554677","https://openalex.org/W2194775991","https://openalex.org/W2211996548","https://openalex.org/W2518599539","https://openalex.org/W2561196672","https://openalex.org/W2740667773","https://openalex.org/W2777511827","https://openalex.org/W2962680827","https://openalex.org/W2962884579","https://openalex.org/W2964211037","https://openalex.org/W2998449272","https://openalex.org/W3034453930","https://openalex.org/W3107653507","https://openalex.org/W3107944836","https://openalex.org/W3108318504","https://openalex.org/W3113414867","https://openalex.org/W3113755791","https://openalex.org/W3122006940","https://openalex.org/W3156154235","https://openalex.org/W3177087374","https://openalex.org/W3204446219","https://openalex.org/W3207493400","https://openalex.org/W4205688290","https://openalex.org/W4212823076","https://openalex.org/W4221167012","https://openalex.org/W4221167637","https://openalex.org/W4226080771","https://openalex.org/W4226216113","https://openalex.org/W4294255647","https://openalex.org/W4304092040","https://openalex.org/W4308449898","https://openalex.org/W4312364648","https://openalex.org/W4312647976","https://openalex.org/W4312933868","https://openalex.org/W4313025803","https://openalex.org/W4386065512","https://openalex.org/W4386066371","https://openalex.org/W4387249787","https://openalex.org/W4387757595","https://openalex.org/W4388283736","https://openalex.org/W4388895055","https://openalex.org/W4390874575","https://openalex.org/W4391968488","https://openalex.org/W4394593148"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,21,33,57,84,98,113,122,126,134,147,171,183,194,208],"development":[2],"of":[3,36,87,125,196],"deep":[4],"learning,":[5],"salient":[6],"object":[7],"detection":[8],"(SOD)":[9],"has":[10],"made":[11],"significant":[12],"progress.":[13],"However,":[14],"this":[15,43],"advancement":[16],"is":[17,173],"often":[18],"constrained":[19],"by":[20],"requirement":[22],"for":[23,56],"extensive":[24],"training":[25,143],"data":[26,51],"and":[27,39,52,66,77,108,140,165,182,211],"expensive":[28],"manual":[29],"annotation.":[30],"To":[31],"eliminate":[32],"laborious":[34],"cost":[35],"dataset":[37],"collection":[38],"pixel-level":[40],"annotation,":[41],"in":[42],"work,":[44],"we":[45,61,96,120,150],"employ":[46,141],"Stable":[47,81],"Diffusion":[48],"to":[49,130,144,175,192],"synthesize":[50],"subsequently":[53],"automate":[54],"annotation":[55,220],"SOD":[58,115,128,156],"task.":[59],"Firstly,":[60],"design":[62,151],"a":[63,152,160],"unified":[64],"prompt":[65],"ChatGPT4":[67],"driven":[68],"diverse":[69],"prompts,":[70],"which":[71,104,158],"guide":[72],"generating":[73],"images":[74,90],"with":[75],"simple":[76,94,99,153],"complex":[78,118,135],"scenes":[79],"using":[80,133],"Diffusion.":[82],"Secondly,":[83],"reliable":[85],"pseudo-labels":[86,132],"these":[88],"synthetic":[89],"are":[91],"generated.":[92],"For":[93,117],"images,":[95,119],"propose":[97],"pseudo-label":[100,136],"generation":[101,137],"(SPLG)":[102],"strategy":[103],"combines":[105,159],"SAM":[106],"segmentation":[107],"CLIP":[109],"classifier,":[110],"then":[111],"train":[112],"initial":[114,127],"model.":[116],"utilize":[121],"inference":[123],"capability":[124],"model":[129,157],"generate":[131],"(CPLG)":[138],"strategy,":[139],"iterative":[142],"dynamically":[145],"update":[146],"pseudo-labels.":[148],"Finally,":[149],"yet":[154],"effective":[155],"feature":[161],"fusion":[162],"module":[163,169],"(FFM)":[164],"an":[166],"edge":[167],"enhancement":[168],"(EEM),":[170],"former":[172],"employed":[174],"extract":[176],"saliency":[177,197],"via":[178],"fusing":[179],"high-level":[180],"features,":[181],"latter":[184],"extracts":[185],"spatial":[186],"positional":[187],"information":[188],"from":[189],"low-level":[190],"features":[191],"enhance":[193],"edges":[195],"results.":[198],"Experiments":[199],"on":[200],"five":[201],"benchmarks":[202],"show":[203],"that":[204],"our":[205],"method":[206],"outperforms":[207],"unannotated":[209],"methods,":[210],"also":[212],"demonstrates":[213],"better":[214],"or":[215],"comparable":[216],"performance":[217],"than":[218],"weak":[219],"based":[221],"methods.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}