{"id":"https://openalex.org/W7140197147","doi":"https://doi.org/10.48550/arxiv.2603.20782","title":"MEMO: Human-like Crisp Edge Detection Using Masked Edge Prediction","display_name":"MEMO: Human-like Crisp Edge Detection Using Masked Edge Prediction","publication_year":2026,"publication_date":"2026-03-21","ids":{"openalex":"https://openalex.org/W7140197147","doi":"https://doi.org/10.48550/arxiv.2603.20782"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.20782","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20782","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.20782","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Cheng, Jiaxin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Jiaxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wu, Yue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Zhou, Yicong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yicong","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":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/T10036","display_name":"Advanced Neural Network Applications","score":0.41850000619888306,"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":0.41850000619888306,"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":0.1136000007390976,"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":0.09459999948740005,"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/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.8047999739646912},{"id":"https://openalex.org/keywords/edge-detection","display_name":"Edge detection","score":0.6168000102043152},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5899999737739563},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5559999942779541},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4510999917984009},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.38659998774528503}],"concepts":[{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.8047999739646912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7240999937057495},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.6168000102043152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5902000069618225},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5899999737739563},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5559999942779541},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4510999917984009},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3725999891757965},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35740000009536743},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3228999972343445},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29339998960494995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2623000144958496}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.20782","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20782","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.20782","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20782","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Learning-based":[0],"edge":[1,12,59,89,134,162,183],"detection":[2],"models":[3],"trained":[4],"with":[5],"cross-entropy":[6,81],"loss":[7,37],"often":[8],"suffer":[9],"from":[10,16],"thick":[11,133],"predictions,":[13],"which":[14,72],"deviate":[15],"the":[17,66,143,148],"crisp,":[18],"single-pixel":[19],"annotations":[20],"typically":[21,136],"provided":[22],"by":[23],"humans.":[24],"While":[25],"previous":[26],"approaches":[27],"to":[28,56,91,116],"achieving":[29],"crisp":[30,77],"edges":[31,78,118],"have":[32],"focused":[33],"on":[34,100,189],"designing":[35],"specialized":[36],"functions":[38],"or":[39],"modifying":[40],"network":[41],"architectures,":[42],"we":[43,64,152],"show":[44],"that":[45,132,159],"a":[46,86,105,138,154],"carefully":[47],"designed":[48],"training":[49],"and":[50,76,145,172,185],"inference":[51,130],"strategy":[52,158],"alone":[53],"is":[54,131],"sufficient":[55],"achieve":[57],"human-like":[58,182],"quality.":[60],"In":[61],"this":[62],"work,":[63],"introduce":[65],"Masked":[67],"Edge":[68],"Prediction":[69],"MOdel":[70],"(MEMO),":[71],"produces":[73],"both":[74],"accurate":[75],"using":[79],"only":[80,104],"loss.":[82],"We":[83],"first":[84],"construct":[85],"large-scale":[87],"synthetic":[88],"dataset":[90],"pre-train":[92],"MEMO,":[93],"enhancing":[94],"its":[95],"generalization":[96],"ability.":[97],"Subsequent":[98],"fine-tuning":[99],"downstream":[101],"datasets":[102],"requires":[103],"lightweight":[106],"module":[107],"comprising":[108],"1.2\\%":[109],"additional":[110],"parameters.":[111],"During":[112],"training,":[113],"MEMO":[114],"learns":[115],"predict":[117],"under":[119],"varying":[120],"ratios":[121],"of":[122,166],"input":[123],"masking.":[124],"A":[125],"key":[126],"insight":[127],"guiding":[128],"our":[129],"predictions":[135,163],"exhibit":[137],"confidence":[139],"gradient:":[140],"high":[141],"in":[142,164,170],"center":[144],"lower":[146],"toward":[147],"boundaries.":[149],"Leveraging":[150],"this,":[151],"propose":[153],"novel":[155],"progressive":[156],"prediction":[157,167],"sequentially":[160],"finalizes":[161],"order":[165],"confidence,":[168],"resulting":[169],"thinner":[171],"more":[173],"precise":[174],"contours.":[175],"Our":[176],"method":[177],"achieves":[178],"visually":[179],"appealing,":[180],"post-processing-free,":[181],"maps":[184],"outperforms":[186],"prior":[187],"methods":[188],"crispness-aware":[190],"evaluations.":[191]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-25T00:00:00"}