{"id":"https://openalex.org/W4405709208","doi":"https://doi.org/10.1109/iscslp63861.2024.10800691","title":"Mitigating Hallucination in Visual Language Model Segmentation with Negative Sampling","display_name":"Mitigating Hallucination in Visual Language Model Segmentation with Negative Sampling","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709208","doi":"https://doi.org/10.1109/iscslp63861.2024.10800691"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5112362321","display_name":"Tong Lee Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tong Lee Chung","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101705358","display_name":"Jun Cheng","orcid":"https://orcid.org/0000-0002-3131-3275"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Cheng","raw_affiliation_strings":["Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040709029","display_name":"Jianxin Pang","orcid":"https://orcid.org/0000-0002-3985-5802"},"institutions":[{"id":"https://openalex.org/I4210135242","display_name":"Omnitech Robotics (United States)","ror":"https://ror.org/03dhfj813","country_code":"US","type":"company","lineage":["https://openalex.org/I4210135242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianxin Pang","raw_affiliation_strings":["Research Institute of UBTech Robotics"],"affiliations":[{"raw_affiliation_string":"Research Institute of UBTech Robotics","institution_ids":["https://openalex.org/I4210135242"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112362321"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210145761"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2195165,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"344","last_page":"348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9848999977111816,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9848999977111816,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9544000029563904,"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/T12536","display_name":"Topological and Geometric Data Analysis","score":0.9390000104904175,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/visual-hallucination","display_name":"Visual Hallucination","score":0.7347615957260132},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6509959101676941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5890073180198669},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5247357487678528},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5237186551094055},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5170734524726868},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4952758848667145},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43036267161369324},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4233558177947998},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.15140488743782043},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.09252145886421204}],"concepts":[{"id":"https://openalex.org/C2908998935","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Visual Hallucination","level":2,"score":0.7347615957260132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6509959101676941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5890073180198669},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5247357487678528},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5237186551094055},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5170734524726868},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4952758848667145},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43036267161369324},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4233558177947998},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.15140488743782043},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.09252145886421204},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800691","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.47999998927116394,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2782368579","https://openalex.org/W2884561390","https://openalex.org/W2962735233","https://openalex.org/W2963350250","https://openalex.org/W2971190479","https://openalex.org/W3174131299","https://openalex.org/W4225385501","https://openalex.org/W4294170691","https://openalex.org/W4385570140","https://openalex.org/W4386076065","https://openalex.org/W4389519620","https://openalex.org/W4389523832","https://openalex.org/W4393160204","https://openalex.org/W6771964179","https://openalex.org/W6777179611","https://openalex.org/W6778883912","https://openalex.org/W6783990618","https://openalex.org/W6791353385","https://openalex.org/W6810334672","https://openalex.org/W6810738896","https://openalex.org/W6851592950","https://openalex.org/W6851950068","https://openalex.org/W6856224812"],"related_works":["https://openalex.org/W2419430421","https://openalex.org/W2334811251","https://openalex.org/W2386464051","https://openalex.org/W32883749","https://openalex.org/W2308791691","https://openalex.org/W1972094787","https://openalex.org/W1971933602","https://openalex.org/W39816624","https://openalex.org/W2002427771","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,13,22,51,111,122,134],"Multi":[3],"Modal":[4],"Language":[5,123],"Models":[6],"(MMLMs)":[7],"have":[8],"led":[9],"to":[10,43,72,108],"major":[11],"breakthroughs":[12],"object":[14,136],"reasoning":[15],"segmentation,":[16],"which":[17,47],"plays":[18],"an":[19,52],"important":[20],"role":[21],"human":[23],"robot":[24],"interaction.":[25],"However,":[26],"hallucination":[27,110],"arises":[28],"when":[29,41],"these":[30],"systems":[31,115],"encounter":[32],"the":[33,54],"task":[34],"of":[35,60,96],"segmenting":[36],"non-existing":[37],"objects,":[38],"for":[39],"example,":[40],"asked":[42],"segment":[44],"a":[45,58,98],"cat":[46],"does":[48,88],"not":[49,89],"appear":[50],"image,":[53],"system":[55],"will":[56],"output":[57],"patch":[59],"false":[61,118],"positive":[62,119],"pixels.":[63],"In":[64],"this":[65,74],"paper,":[66],"we":[67],"utilizes":[68],"negative":[69,83],"sampling":[70],"approach":[71,87],"address":[73],"issue.":[75],"Unlike":[76],"other":[77],"approaches":[78],"that":[79],"require":[80,90],"acquiring":[81],"new":[82],"training":[84],"data,":[85],"our":[86],"any":[91],"extra":[92],"data":[93],"and":[94,116],"tuning":[95],"only":[97],"few":[99],"hundred":[100],"steps":[101],"is":[102],"needed.":[103],"We":[104],"conduct":[105],"extensive":[106],"experiments":[107],"identify":[109],"MMLM":[112],"based":[113],"segmentation":[114],"mitigate":[117],"pixel":[120],"rate":[121],"Instructed":[124],"Segmentation":[125],"Assistant":[126],"(LISA)":[127],"by":[128],"50%":[129],"while":[130],"maintaining":[131],"similar":[132],"performance":[133],"existing":[135],"segmentation.":[137]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}