{"id":"https://openalex.org/W4417455720","doi":"https://doi.org/10.48550/arxiv.2512.13175","title":"Seeing the Whole Picture: Distribution-Guided Data-Free Distillation for Semantic Segmentation","display_name":"Seeing the Whole Picture: Distribution-Guided Data-Free Distillation for Semantic Segmentation","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W4417455720","doi":"https://doi.org/10.48550/arxiv.2512.13175"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2512.13175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.13175","pdf_url":"https://arxiv.org/pdf/2512.13175","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.13175","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sun, Hongxuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Hongxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043100976","display_name":"Tao Wu","orcid":"https://orcid.org/0000-0001-6469-9613"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.7023000121116638,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.7023000121116638,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.11330000311136246,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.09759999811649323,"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":0.6535000205039978},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6345000267028809},{"id":"https://openalex.org/keywords/mirroring","display_name":"Mirroring","score":0.4778999984264374},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.47029998898506165},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.39559999108314514},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.29660001397132874},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.29649999737739563},{"id":"https://openalex.org/keywords/semantic-mapping","display_name":"Semantic mapping","score":0.29600000381469727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516999840736389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6590999960899353},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6535000205039978},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6345000267028809},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49070000648498535},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.4778999984264374},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.265500009059906},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2512.13175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.13175","pdf_url":"https://arxiv.org/pdf/2512.13175","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.13175","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.13175","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.13175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.13175","pdf_url":"https://arxiv.org/pdf/2512.13175","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417455720.pdf","grobid_xml":"https://content.openalex.org/works/W4417455720.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Semantic":[0],"segmentation":[1,49],"requires":[2],"a":[3,57,94],"holistic":[4],"understanding":[5],"of":[6,80,106,157],"the":[7,75,104,111,140,154],"physical":[8],"world,":[9],"as":[10],"it":[11],"assigns":[12],"semantic":[13,64,177],"labels":[14],"to":[15,24,48,87,97],"spatially":[16],"continuous":[17],"and":[18,77,147],"structurally":[19],"coherent":[20],"objects":[21],"rather":[22],"than":[23],"isolated":[25],"pixels.":[26],"However,":[27],"existing":[28,172],"data-free":[29,59,173],"knowledge":[30],"distillation":[31,60,174],"(DFKD)":[32],"methods-primarily":[33],"designed":[34],"for":[35,63,176],"classification-often":[36],"disregard":[37],"this":[38,52],"continuity,":[39],"resulting":[40],"in":[41,145,159],"significant":[42],"performance":[43],"degradation":[44],"when":[45],"applied":[46],"directly":[47],"tasks.":[50],"In":[51],"paper,":[53],"we":[54,122],"introduce":[55],"DFSS,":[56],"novel":[58],"framework":[61],"tailored":[62],"segmentation.":[65],"Unlike":[66],"prior":[67],"approaches":[68],"that":[69,108,134,168],"treat":[70],"pixels":[71],"independently,":[72],"DFSS":[73,169],"respects":[74],"structural":[76],"contextual":[78],"continuity":[79],"real-world":[81],"scenes.":[82],"Our":[83],"key":[84],"insight":[85],"is":[86],"leverage":[88],"Batch":[89],"Normalization":[90],"(BN)":[91],"statistics":[92],"from":[93],"teacher":[95,119],"model":[96],"guide":[98],"Approximate":[99],"Distribution":[100,125],"Sampling":[101],"(ADS),":[102],"enabling":[103],"selection":[105],"data":[107,142],"better":[109],"reflects":[110],"original":[112,141],"training":[113,146],"distribution-without":[114],"relying":[115],"on":[116,164,186],"potentially":[117],"misleading":[118],"predictions.":[120],"Additionally,":[121],"propose":[123],"Weighted":[124],"Progressive":[126],"Distillation":[127],"(WDPD),":[128],"which":[129],"dynamically":[130],"prioritizes":[131],"reliable":[132],"samples":[133],"are":[135],"more":[136,150],"closely":[137],"aligned":[138],"with":[139,182],"distribution":[143],"early":[144],"gradually":[148],"incorporates":[149],"challenging":[151],"cases,":[152],"mirroring":[153],"natural":[155],"progression":[156],"learning":[158],"human":[160],"perception.":[161],"Extensive":[162],"experiments":[163],"standard":[165],"benchmarks":[166],"demonstrate":[167],"consistently":[170],"outperforms":[171],"methods":[175],"segmentation,":[178],"achieving":[179],"state-of-the-art":[180],"results":[181],"significantly":[183],"reduced":[184],"reliance":[185],"auxiliary":[187],"data.":[188]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-12-17T00:00:00"}