{"id":"https://openalex.org/W6979299658","doi":null,"title":"PicoSAM2: Low-Latency Segmentation In-Sensor for Edge Vision Applications","display_name":"PicoSAM2: Low-Latency Segmentation In-Sensor for Edge Vision Applications","publication_year":2025,"publication_date":"2025-06-23","ids":{"openalex":"https://openalex.org/W6979299658"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.18807","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.18807","pdf_url":"https://arxiv.org/pdf/2506.18807","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.18807","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bonazzi, Pietro","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bonazzi, Pietro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033981189","display_name":"Nicola Farronato","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farronato, Nicola","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106689444","display_name":"Stefan Zihlmann","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihlmann, Stefan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044945190","display_name":"Haotong Qin","orcid":"https://orcid.org/0000-0001-7391-7539","observed_orcids":["https://orcid.org/0000-0001-7391-7539"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Haotong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066423975","display_name":"Michele Magno","orcid":"https://orcid.org/0000-0003-0368-8923","observed_orcids":["https://orcid.org/0000-0003-0368-8923"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Magno, Michele","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":true,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00039999998989515007,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/segment-anything-model-2","display_name":"Segment Anything Model 2","score":0.7950000166893005},{"id":"https://openalex.org/keywords/prompt-based-segmentation","display_name":"prompt-based segmentation","score":0.6150000095367432},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.8140000104904175},{"id":"https://openalex.org/keywords/neural-network-quantization","display_name":"neural network quantization","score":0.5879999995231628},{"id":"https://openalex.org/keywords/smart-glasses","display_name":"smart glasses","score":0.8410000205039978},{"id":"https://openalex.org/keywords/iot-devices","display_name":"IoT devices","score":0.7770000100135803}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7699000239372253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7394999861717224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7368999719619751},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6669999957084656},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5608999729156494},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5440999865531921},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.4336000084877014},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.41749998927116394},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.41659998893737793},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.3531999886035919},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.31200000643730164},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.30079999566078186},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C40305131","wikidata":"https://www.wikidata.org/wiki/Q2616305","display_name":"Obfuscation","level":2,"score":0.2662000060081482}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2506.18807","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.18807","pdf_url":"https://arxiv.org/pdf/2506.18807","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.18807","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.18807","pdf_url":"https://arxiv.org/pdf/2506.18807","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,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Real-time,":[0],"on-device":[1],"segmentation":[2,26,115],"is":[3,116],"critical":[4],"for":[5,29,96],"latency-sensitive":[6],"and":[7,13,31,48,63,68,93,106],"privacy-aware":[8],"applications":[9],"like":[10],"smart":[11],"glasses":[12],"IoT":[14],"devices.":[15],"We":[16],"introduce":[17],"PicoSAM2,":[18],"a":[19,41],"lightweight":[20],"(1.3M":[21],"parameters,":[22],"336M":[23],"MACs)":[24],"promptable":[25,114],"model":[27,74,89],"optimized":[28],"edge":[30],"in-sensor":[32,97],"execution,":[33],"including":[34],"the":[35,55,81,87],"Sony":[36],"IMX500.":[37],"It":[38],"builds":[39],"on":[40,80],"depthwise":[42],"separable":[43],"U-Net,":[44],"with":[45],"knowledge":[46],"distillation":[47],"fixed-point":[49],"prompt":[50],"encoding":[51],"to":[52],"learn":[53],"from":[54],"Segment":[56],"Anything":[57],"Model":[58],"2":[59],"(SAM2).":[60],"On":[61],"COCO":[62],"LVIS,":[64],"it":[65,86],"achieves":[66],"51.9%":[67],"44.9%":[69],"mIoU,":[70],"respectively.":[71],"The":[72],"quantized":[73],"(1.22MB)":[75],"runs":[76],"at":[77],"14.3":[78],"ms":[79],"IMX500-achieving":[82],"86":[83],"MACs/cycle,":[84],"making":[85],"only":[88],"meeting":[90],"both":[91],"memory":[92],"compute":[94],"constraints":[95],"deployment.":[98],"Distillation":[99],"boosts":[100],"LVIS":[101],"performance":[102],"by":[103],"+3.5%":[104],"mIoU":[105],"+5.1%":[107],"mAP.":[108],"These":[109],"results":[110],"demonstrate":[111],"that":[112],"efficient,":[113],"feasible":[117],"directly":[118],"on-camera,":[119],"enabling":[120],"privacy-preserving":[121],"vision":[122],"without":[123],"cloud":[124],"or":[125],"host":[126],"processing.":[127]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-10T00:00:00"}