{"id":"https://openalex.org/W3109628940","doi":"https://doi.org/10.1109/cisp-bmei51763.2020.9263683","title":"A Saliency-based Weakly-supervised Network for Fine-Grained Image Categorization","display_name":"A Saliency-based Weakly-supervised Network for Fine-Grained Image Categorization","publication_year":2020,"publication_date":"2020-10-17","ids":{"openalex":"https://openalex.org/W3109628940","doi":"https://doi.org/10.1109/cisp-bmei51763.2020.9263683","mag":"3109628940"},"language":"en","primary_location":{"id":"doi:10.1109/cisp-bmei51763.2020.9263683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cisp-bmei51763.2020.9263683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012604710","display_name":"Yawen Han","orcid":"https://orcid.org/0009-0007-3481-2700"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yawen Han","raw_affiliation_strings":["Communication University of China,School of Information and Communication Engineering,Beijing,China","School of Information and Communication Engineering, Communication University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Communication University of China,School of Information and Communication Engineering,Beijing,China","institution_ids":["https://openalex.org/I75689368"]},{"raw_affiliation_string":"School of Information and Communication Engineering, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100400486","display_name":"Meng Fang","orcid":"https://orcid.org/0000-0001-6745-286X"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Meng","raw_affiliation_strings":["Communication University of China,School of Information and Communication Engineering,Beijing,China","School of Information and Communication Engineering, Communication University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Communication University of China,School of Information and Communication Engineering,Beijing,China","institution_ids":["https://openalex.org/I75689368"]},{"raw_affiliation_string":"School of Information and Communication Engineering, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012604710"],"corresponding_institution_ids":["https://openalex.org/I75689368"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.14124151,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"270","last_page":"274"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9991999864578247,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.998199999332428,"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/pooling","display_name":"Pooling","score":0.7861797213554382},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7706506252288818},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7449324131011963},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7110454440116882},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.7065205574035645},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.6806213855743408},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6358674764633179},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6258959770202637},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5525535941123962},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.542750358581543},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5130409002304077},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4969806969165802},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.45075246691703796},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44669294357299805},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44402673840522766},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3614107668399811},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2746754288673401},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1397673487663269}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7861797213554382},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706506252288818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7449324131011963},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7110454440116882},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.7065205574035645},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.6806213855743408},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6358674764633179},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6258959770202637},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5525535941123962},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.542750358581543},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5130409002304077},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4969806969165802},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.45075246691703796},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44669294357299805},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44402673840522766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3614107668399811},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2746754288673401},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1397673487663269},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cisp-bmei51763.2020.9263683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cisp-bmei51763.2020.9263683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W603908379","https://openalex.org/W1797268635","https://openalex.org/W1821462560","https://openalex.org/W1836465849","https://openalex.org/W2104657103","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2295107390","https://openalex.org/W2737725206","https://openalex.org/W2765268259","https://openalex.org/W2883502031","https://openalex.org/W2889469641","https://openalex.org/W2986821660","https://openalex.org/W6618372016","https://openalex.org/W6638319203","https://openalex.org/W6638667902"],"related_works":["https://openalex.org/W2950524887","https://openalex.org/W2883502031","https://openalex.org/W2022849497","https://openalex.org/W2261271299","https://openalex.org/W2963066927","https://openalex.org/W4280638452","https://openalex.org/W3111811104","https://openalex.org/W4380083739","https://openalex.org/W3081299480","https://openalex.org/W2407190427"],"abstract_inverted_index":{"Fine-grained":[0],"image":[1,26],"categorization":[2,27],"is":[3,14],"to":[4,84],"recognize":[5],"subcategories":[6],"from":[7,42],"each":[8],"other.":[9],"In":[10,48],"actual":[11],"photographs,":[12],"there":[13],"often":[15,40],"large":[16],"intra-class":[17],"variation":[18],"and":[19,37,92,111],"small":[20],"inter-class":[21],"variation,":[22],"which":[23],"make":[24],"fine-grained":[25],"a":[28,53,57],"challenging":[29],"task.":[30],"Existing":[31],"bilinear-pooling-based":[32],"methods":[33,39],"are":[34,109],"less":[35],"interpretable,":[36],"visual-attention-based":[38],"suffer":[41],"limited":[43],"number":[44],"of":[45,68,106],"salient":[46,66],"part.":[47],"this":[49],"paper,":[50],"we":[51,78],"propose":[52],"saliency-based":[54],"weakly-supervised":[55],"network,":[56],"simple":[58],"approach":[59],"that":[60,104],"can":[61],"effectively":[62],"preserve":[63],"all":[64],"the":[65,69,74,86],"details":[67],"original":[70],"image.":[71],"Based":[72],"on":[73,99],"saliency":[75,87],"sampler":[76],"backbone,":[77],"apply":[79],"feature":[80],"pyramid":[81],"network":[82,108],"structure":[83],"combine":[85],"information":[88],"with":[89],"high-level":[90],"features":[91],"use":[93],"KL-divergence":[94],"for":[95],"knowledge":[96],"distillation.":[97],"Experiments":[98],"Caltech-UCSD":[100],"Birds":[101],"dataset":[102],"show":[103],"components":[105],"our":[107],"efficient":[110],"reliable.":[112]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}