{"id":"https://openalex.org/W3135360951","doi":null,"title":"GANav: Group-wise Attention Network for Classifying Navigable Regions in Unstructured Outdoor Environments.","display_name":"GANav: Group-wise Attention Network for Classifying Navigable Regions in Unstructured Outdoor Environments.","publication_year":2021,"publication_date":"2021-03-07","ids":{"openalex":"https://openalex.org/W3135360951","mag":"3135360951"},"language":"en","primary_location":{"id":"mag:3135360951","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2103.04233.pdf","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,"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":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2103.04233.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014003390","display_name":"Tianrui Guan","orcid":"https://orcid.org/0000-0002-6892-9778","observed_orcids":["https://orcid.org/0000-0002-6892-9778"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianrui Guan","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6892-9778","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101761284","display_name":"Divya Kothandaraman","orcid":"https://orcid.org/0000-0002-6276-4968","observed_orcids":["https://orcid.org/0000-0002-6276-4968"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Divya Kothandaraman","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6276-4968","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016704715","display_name":"Rohan Chandra","orcid":"https://orcid.org/0000-0003-4843-6375","observed_orcids":["https://orcid.org/0000-0003-4843-6375"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohan Chandra","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4843-6375","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801","observed_orcids":["https://orcid.org/0000-0001-7047-9801"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7047-9801","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":8,"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":0.9634000062942505,"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":0.9634000062942505,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.0142000000923872,"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":0.00430000014603138,"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/off-road-terrain","display_name":"off-road terrain","score":0.8980000019073486},{"id":"https://openalex.org/keywords/unstructured-outdoor-environments","display_name":"unstructured outdoor environments","score":0.8259999752044678},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.5649999976158142},{"id":"https://openalex.org/keywords/long-tailed-data","display_name":"long-tailed data","score":0.7950000166893005},{"id":"https://openalex.org/keywords/rgb-images","display_name":"RGB images","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7523542642593384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6995360851287842},{"id":"https://openalex.org/C2778972660","wikidata":"https://www.wikidata.org/wiki/Q1666353","display_name":"Navigability","level":2,"score":0.6989956498146057},{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.5796265006065369},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.546795129776001},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5128722190856934},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4997696876525879},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.4716324508190155},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.42884039878845215},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3619440197944641},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.352636456489563},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.13939303159713745},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.11716341972351074},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3135360951","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2103.04233.pdf","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,"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":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3135360951","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2103.04233.pdf","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,"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":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W243059481","https://openalex.org/W1861492603","https://openalex.org/W2024139303","https://openalex.org/W2031489346","https://openalex.org/W2089652819","https://openalex.org/W2113986333","https://openalex.org/W2117211893","https://openalex.org/W2209211308","https://openalex.org/W2319778224","https://openalex.org/W2395611524","https://openalex.org/W2560023338","https://openalex.org/W2598666589","https://openalex.org/W2737258237","https://openalex.org/W2743627947","https://openalex.org/W2750929583","https://openalex.org/W2757216539","https://openalex.org/W2765242627","https://openalex.org/W2783763209","https://openalex.org/W2885121946","https://openalex.org/W2895340641","https://openalex.org/W2950703314","https://openalex.org/W2955058313","https://openalex.org/W2959840911","https://openalex.org/W2963150697","https://openalex.org/W2963606038","https://openalex.org/W2963691377","https://openalex.org/W2963759070","https://openalex.org/W2964309882","https://openalex.org/W2976122994","https://openalex.org/W3003922739","https://openalex.org/W3006388420","https://openalex.org/W3016889634","https://openalex.org/W3082486589","https://openalex.org/W3119762560","https://openalex.org/W3122484828","https://openalex.org/W3180562345","https://openalex.org/W3206164009"],"related_works":["https://openalex.org/W6922505421","https://openalex.org/W4285304415","https://openalex.org/W4410274261","https://openalex.org/W7136326202","https://openalex.org/W4401840984","https://openalex.org/W7203934323","https://openalex.org/W7164165143","https://openalex.org/W7162642180","https://openalex.org/W7167806165","https://openalex.org/W7164861522"],"abstract_inverted_index":{"We":[0,39,99,125],"present":[1],"a":[2,41,50,84],"new":[3],"learning-based":[4],"method":[5],"for":[6,123],"identifying":[7],"safe":[8],"and":[9,15,76,107,135,147],"navigable":[10],"regions":[11],"in":[12,120],"off-road":[13,121],"terrains":[14,122],"unstructured":[16],"environments":[17],"from":[18],"RGB":[19],"images.":[20],"Our":[21],"approach":[22,128],"consists":[23],"of":[24,27,60,96,117],"classifying":[25],"groups":[26,75],"terrain":[28],"classes":[29],"based":[30],"on":[31,72,104,132,145,149],"their":[32],"navigability":[33,58],"levels":[34,59],"using":[35],"coarse-grained":[36],"semantic":[37],"segmentation.":[38],"propose":[40,83],"bottleneck":[42],"transformer-based":[43],"deep":[44],"neural":[45],"network":[46,68],"architecture":[47],"that":[48,110],"uses":[49],"novel":[51],"group-wise":[52,63],"attention":[53,64],"mechanism":[54],"to":[55,69,91],"distinguish":[56],"between":[57],"different":[61,74],"terrains.Our":[62],"heads":[65],"enable":[66],"the":[67,73,78,93,97,105,115,140],"explicitly":[70],"focus":[71],"improve":[77],"accuracy.":[79],"In":[80],"addition,":[81],"we":[82],"dynamic":[85],"weighted":[86],"cross":[87],"entropy":[88],"loss":[89],"function":[90],"handle":[92],"long-tailed":[94],"nature":[95],"dataset.":[98],"show":[100],"through":[101],"extensive":[102],"evaluations":[103],"RUGD":[106,146],"RELLIS-3D":[108],"datasets":[109,134],"our":[111,127],"learning":[112],"algorithm":[113],"improves":[114],"accuracy":[116],"visual":[118],"perception":[119],"navigation.":[124],"compare":[126],"with":[129],"prior":[130],"work":[131],"these":[133],"achieve":[136],"an":[137],"improvement":[138],"over":[139],"state-of-the-art":[141],"mIoU":[142],"by":[143],"6.74-39.1%":[144],"3.82-10.64%":[148],"RELLIS-3D.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-03-15T00:00:00"}