{"id":"https://openalex.org/W7127423006","doi":"https://doi.org/10.48550/arxiv.2602.00516","title":"SPARK: Stochastic Propagation via Affinity-guided Random walK for training-free unsupervised segmentation","display_name":"SPARK: Stochastic Propagation via Affinity-guided Random walK for training-free unsupervised segmentation","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7127423006","doi":"https://doi.org/10.48550/arxiv.2602.00516"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.00516","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","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":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120398917","display_name":"Kunal Mahatha","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mahatha, Kunal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122540171","display_name":"Jose Dolz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dolz, Jose","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Desrosiers, Christian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Desrosiers, Christian","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5120398917"],"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.25619998574256897,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.25619998574256897,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.21660000085830688,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.10509999841451645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7666000127792358},{"id":"https://openalex.org/keywords/affinity-propagation","display_name":"Affinity propagation","score":0.6140999794006348},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5659000277519226},{"id":"https://openalex.org/keywords/random-walk","display_name":"Random walk","score":0.5156999826431274},{"id":"https://openalex.org/keywords/markov-random-field","display_name":"Markov random field","score":0.49230000376701355},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4893999993801117},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.430400013923645},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.42719998955726624},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4092000126838684},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4034000039100647}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7666000127792358},{"id":"https://openalex.org/C109659709","wikidata":"https://www.wikidata.org/wiki/Q3407504","display_name":"Affinity propagation","level":5,"score":0.6140999794006348},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5659000277519226},{"id":"https://openalex.org/C121194460","wikidata":"https://www.wikidata.org/wiki/Q856741","display_name":"Random walk","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5044000148773193},{"id":"https://openalex.org/C2778045648","wikidata":"https://www.wikidata.org/wiki/Q176827","display_name":"Markov random field","level":4,"score":0.49230000376701355},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4634000062942505},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.430400013923645},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.42719998955726624},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39169999957084656},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.36739999055862427},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36649999022483826},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.311599999666214},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2994000017642975},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.29670000076293945},{"id":"https://openalex.org/C152948882","wikidata":"https://www.wikidata.org/wiki/Q4060686","display_name":"Belief propagation","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C48903430","wikidata":"https://www.wikidata.org/wiki/Q491370","display_name":"Graph partition","level":3,"score":0.2842999994754791},{"id":"https://openalex.org/C23463724","wikidata":"https://www.wikidata.org/wiki/Q2308831","display_name":"Spectral method","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C5134670","wikidata":"https://www.wikidata.org/wiki/Q1626444","display_name":"Cut","level":4,"score":0.2797999978065491},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25209999084472656},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.00516","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.00516","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.00516","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.00516","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"score":0.5807329416275024,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"argue":[1],"that":[2,14,117,146,156,174],"existing":[3],"training-free":[4,97],"segmentation":[5,15,98,110,171],"methods":[6],"rely":[7],"on":[8,28,137],"an":[9,152],"implicit":[10],"and":[11,32,57,87,187],"limiting":[12],"assumption,":[13],"is":[16],"a":[17,80,100,113,130,142],"spectral":[18,55],"graph":[19,30],"partitioning":[20,31],"problem":[21,104],"over":[22,105],"diffusion-derived":[23],"affinities.":[24],"Such":[25],"approaches,":[26],"based":[27],"global":[29,119],"eigenvector-based":[33],"formulations":[34],"of":[35,48,74],"affinity":[36,65,85,107,134,163],"matrices,":[37],"suffer":[38],"from":[39,112,126],"several":[40],"fundamental":[41],"drawbacks,":[42],"they":[43],"require":[44],"pre-selecting":[45],"the":[46,72],"number":[47],"clusters,":[49],"induce":[50],"boundary":[51],"oversmoothing":[52],"due":[53],"to":[54,61,193],"relaxation,":[56],"remain":[58],"highly":[59],"sensitive":[60],"noisy":[62],"or":[63],"multi-modal":[64],"distributions.":[66],"Moreover,":[67],"many":[68],"prior":[69,194],"works":[70],"neglect":[71],"importance":[73],"local":[75,123],"neighborhood":[76],"structure,":[77],"which":[78],"plays":[79],"crucial":[81],"role":[82],"in":[83],"stabilizing":[84],"propagation":[86,115,144],"preserving":[88],"fine-grained":[89],"contours.":[90],"To":[91],"address":[92],"these":[93],"limitations,":[94],"we":[95,140],"reformulate":[96],"as":[99],"stochastic":[101,114],"flow":[102],"equilibrium":[103],"diffusion-induced":[106],"graphs,":[108],"where":[109],"emerges":[111],"process":[116],"integrates":[118],"diffusion":[120,150],"attention":[121],"with":[122,151],"neighborhoods":[124],"extracted":[125],"stable":[127,190],"diffusion,":[128],"yielding":[129],"sparse":[131],"yet":[132],"expressive":[133],"structure.":[135],"Building":[136],"this":[138],"formulation,":[139],"introduce":[141],"Markov":[143],"scheme":[145],"performs":[147],"random-walk-based":[148],"label":[149],"adaptive":[153],"pruning":[154],"strategy":[155],"suppresses":[157],"unreliable":[158],"transitions":[159],"while":[160],"reinforcing":[161],"confident":[162],"paths.":[164],"Experiments":[165],"across":[166],"seven":[167],"widely":[168],"used":[169],"semantic":[170],"benchmarks":[172],"demonstrate":[173],"our":[175],"method":[176],"achieves":[177],"state-of-the-art":[178],"zero-shot":[179],"performance,":[180],"producing":[181],"sharper":[182],"boundaries,":[183],"more":[184,189],"coherent":[185],"regions,":[186],"significantly":[188],"masks":[191],"compared":[192],"spectral-clustering-based":[195],"approaches.":[196]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-04T00:00:00"}