{"id":"https://openalex.org/W7140935328","doi":"https://doi.org/10.48550/arxiv.2603.23906","title":"GenMask: Adapting DiT for Segmentation via Direct Mask Generation","display_name":"GenMask: Adapting DiT for Segmentation via Direct Mask Generation","publication_year":2026,"publication_date":"2026-03-25","ids":{"openalex":"https://openalex.org/W7140935328","doi":"https://doi.org/10.48550/arxiv.2603.23906"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.23906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23906","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.2603.23906","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130664881","display_name":"Yuhuan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yang, Yuhuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007384127","display_name":"Xianwei Zhuang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Xianwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130693381","display_name":"Yuxuan Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Yuxuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130698843","display_name":"Chaofan Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Chaofan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130699366","display_name":"Shuai Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Shuai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130702112","display_name":"Jiangchao Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Jiangchao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130708595","display_name":"Ya Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130671871","display_name":"Junyang Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Junyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130661633","display_name":"Yanfeng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yanfeng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5130664881"],"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":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8671000003814697,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8671000003814697,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.06310000270605087,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.013899999670684338,"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":0.7810999751091003},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.5666000247001648},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5468000173568726},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5167999863624573},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4966999888420105},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4961000084877014},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.44830000400543213},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.38530001044273376},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.3837999999523163}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7810999751091003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7592999935150146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360000014305115},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.5666000247001648},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5616999864578247},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5468000173568726},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5167999863624573},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4966999888420105},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4961000084877014},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.44830000400543213},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3537999987602234},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.30410000681877136},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.23906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23906","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.2603.23906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23906","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"approaches":[1],"for":[2,105,113,118,164],"segmentation":[3,13,59,114,134,165,176],"have":[4],"leveraged":[5],"pretrained":[6],"generative":[7,67,147],"models":[8],"as":[9,14,136,138],"feature":[10,21,39,160],"extractors,":[11],"treating":[12],"a":[15,28,66,71,128],"downstream":[16],"adaptation":[17],"task":[18],"via":[19],"indirect":[20,38,57],"retrieval.":[22],"This":[23],"implicit":[24],"use":[25],"suffers":[26],"from":[27,92],"fundamental":[29],"misalignment":[30],"in":[31,65,141],"representation.":[32],"It":[33],"also":[34],"depends":[35],"heavily":[36],"on":[37,172],"extraction":[40,161],"pipelines,":[41],"which":[42],"complicate":[43],"the":[44,145,151,157,181],"workflow":[45],"and":[46,88,115,174,178],"limit":[47],"adaptation.":[48],"In":[49],"this":[50,75,98],"paper,":[51],"we":[52,100],"argue":[53],"that":[54,108],"instead":[55],"of":[56,80,159,183],"adaptation,":[58],"tasks":[60],"should":[61],"be":[62],"trained":[63],"directly":[64],"manner.":[68],"We":[69,125],"identify":[70],"key":[72],"obstacle":[73],"to":[74,131],"unified":[76],"formulation:":[77],"VAE":[78],"latents":[79],"binary":[81,106],"masks":[82,107,135],"are":[83],"sharply":[84],"distributed,":[85],"noise":[86,111,117],"robust,":[87],"linearly":[89],"separable,":[90],"distinct":[91],"natural":[93],"image":[94,119],"latents.":[95],"To":[96],"bridge":[97],"gap,":[99],"introduce":[101],"timesteps":[102],"sampling":[103],"strategy":[104],"emphasizes":[109],"extreme":[110],"levels":[112],"moderate":[116],"generation,":[120],"enabling":[121],"harmonious":[122],"joint":[123],"training.":[124],"present":[126],"GenMask,":[127],"DiT":[129,153],"trains":[130],"generate":[132],"black-and-white":[133],"well":[137],"colorful":[139],"images":[140],"RGB":[142],"space":[143],"under":[144],"original":[146,152],"objective.":[148],"GenMask":[149,168],"preserves":[150],"architecture":[154],"while":[155],"removing":[156],"need":[158],"pipelines":[162],"tailored":[163],"tasks.":[166],"Empirically,":[167],"attains":[169],"state-of-the-art":[170],"performance":[171],"referring":[173],"reasoning":[175],"benchmarks":[177],"ablations":[179],"quantify":[180],"contribution":[182],"each":[184],"component.":[185]},"counts_by_year":[],"updated_date":"2026-03-28T06:11:35.319607","created_date":"2026-03-27T00:00:00"}