{"id":"https://openalex.org/W6987664880","doi":null,"title":"Towards better fine-grained visual classification: an attention-based, hierarchical approach","display_name":"Towards better fine-grained visual classification: an attention-based, hierarchical approach","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W6987664880"},"language":"en","primary_location":{"id":"pmh:oai:dr.ntu.edu.sg:10356/167399","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/167399","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Final Year Project (FYP)"},"volume":null,"type":"report","is_traditional":false,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Gao, Manrong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gao, Manrong","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":0.9473000168800354,"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":0.9473000168800354,"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":0.04540000110864639,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.005200000014156103,"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/fine-grained-image-classification","display_name":"fine-grained image classification","score":0.9990000128746033},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.6549999713897705},{"id":"https://openalex.org/keywords/hierarchical-classification","display_name":"hierarchical classification","score":0.9480000138282776},{"id":"https://openalex.org/keywords/multi-branch-network","display_name":"multi-branch network","score":0.5529999732971191},{"id":"https://openalex.org/keywords/bird-species-classification","display_name":"bird species classification","score":0.6019999980926514}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8123999834060669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7552000284194946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6757000088691711},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5856000185012817},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5616999864578247},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4634000062942505},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4357999861240387},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.43369999527931213},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43290001153945923},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4269999861717224},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38600000739097595},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C124527596","wikidata":"https://www.wikidata.org/wiki/Q17029359","display_name":"Hierarchical control system","level":3,"score":0.3598000109195709},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3172000050544739},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:dr.ntu.edu.sg:10356/167399","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/167399","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Final Year Project (FYP)"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7126448633","https://openalex.org/W7131228885","https://openalex.org/W4413061389","https://openalex.org/W4406857259","https://openalex.org/W3213528704","https://openalex.org/W4392910577","https://openalex.org/W4312521207","https://openalex.org/W4402034293","https://openalex.org/W3005359536","https://openalex.org/W3035367622"],"abstract_inverted_index":{"Unlike":[0],"general":[1],"object":[2],"classification,":[3],"which":[4],"uses":[5],"convolutional":[6],"neural":[7,128],"networks":[8],"(CNNs),":[9],"fine-grained":[10,28,32,84],"visual":[11,139],"classification":[12,44],"(FGVC)":[13],"is":[14],"a":[15,36,92,117,126,138,153],"challenging":[16],"problem":[17],"that":[18],"involves":[19],"categorizing":[20],"objects":[21],"belong":[22],"to":[23,82,91,143],"different":[24,65,107],"subcategories":[25],"with":[26,156],"subtle":[27],"details.":[29],"Furthermore,":[30],"most":[31,146],"categories":[33,63,114],"inherently":[34],"exhibit":[35],"hierarchical":[37,43,56,97,123,154],"structure,":[38],"as":[39],"exemplified":[40],"by":[41,120],"the":[42,100,110,122,145,150],"of":[45,55,86,96,112,134,149],"birds":[46],"into":[47,125],"orders,":[48],"families,":[49],"genera,":[50],"and":[51,115,160],"species.":[52],"This":[53],"type":[54],"structure":[57,124],"can":[58],"capture":[59],"intricate":[60],"relationships":[61],"among":[62],"at":[64],"levels,":[66],"thereby":[67],"assisting":[68],"in":[69,72,99,109],"reducing":[70],"ambiguity":[71],"predictions.":[73],"Existing":[74],"attention-based":[75],"approaches":[76],"focus":[77],"on":[78],"localize":[79],"discriminative":[80,147],"parts":[81,148],"learn":[83],"details":[85],"one":[87,157],"certain":[88],"level":[89],"belongs":[90],"category,":[93],"ignoring":[94],"utilization":[95],"information":[98],"category.":[101],"In":[102],"this":[103],"paper,":[104],"we":[105],"explored":[106],"levels":[108],"hierarchy":[111],"predicting":[113],"proposed":[116,131],"novel":[118],"model":[119,132],"incorporating":[121],"deep":[127],"network.":[129],"The":[130],"consists":[133],"two":[135],"parts:":[136],"1)":[137],"attention":[140],"sampling":[141],"module":[142],"emphasize":[144],"image,":[151],"2)":[152],"classifier":[155],"base":[158],"net":[159],"four":[161],"branch":[162],"nets.":[163]},"counts_by_year":[],"updated_date":"2026-07-14T23:32:53.992493","created_date":"2025-10-10T00:00:00"}