{"id":"https://openalex.org/W3009323727","doi":"https://doi.org/10.1109/wacv45572.2020.9093385","title":"Towards Learning Affine-Invariant Representations via Data-Efficient CNNs","display_name":"Towards Learning Affine-Invariant Representations via Data-Efficient CNNs","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3009323727","doi":"https://doi.org/10.1109/wacv45572.2020.9093385","mag":"3009323727"},"language":"en","primary_location":{"id":"doi:10.1109/wacv45572.2020.9093385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","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/A5031765917","display_name":"Wenju Xu","orcid":"https://orcid.org/0000-0003-2740-0357"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wenju Xu","raw_affiliation_strings":["University of Kansas, KS"],"affiliations":[{"raw_affiliation_string":"University of Kansas, KS","institution_ids":["https://openalex.org/I146416000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399485","display_name":"Guanghui Wang","orcid":"https://orcid.org/0000-0003-3182-104X"},"institutions":[{"id":"https://openalex.org/I146416000","display_name":"University of Kansas","ror":"https://ror.org/001tmjg57","country_code":"US","type":"education","lineage":["https://openalex.org/I146416000"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guanghui Wang","raw_affiliation_strings":["University of Kansas, KS"],"affiliations":[{"raw_affiliation_string":"University of Kansas, KS","institution_ids":["https://openalex.org/I146416000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112353486","display_name":"Alan Sullivan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan Sullivan","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), MA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), MA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048506332","display_name":"Ziming Zhang","orcid":"https://orcid.org/0000-0002-0921-8298"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziming Zhang","raw_affiliation_strings":["Worcester Polytechnic Institute, MA"],"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute, MA","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031765917"],"corresponding_institution_ids":["https://openalex.org/I146416000"],"apc_list":null,"apc_paid":null,"fwci":1.3678,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.83129999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"893","last_page":"902"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"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":0.9993000030517578,"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/T11714","display_name":"Multimodal Machine Learning Applications","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"}}],"keywords":[{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.7579915523529053},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7054989337921143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6272952556610107},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6256516575813293},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5897959470748901},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5675206780433655},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5641345977783203},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49945569038391113},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4834931194782257},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4710181653499603},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4603431522846222},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4303123950958252},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22559800744056702},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.22128349542617798},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20501551032066345}],"concepts":[{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.7579915523529053},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7054989337921143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6272952556610107},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6256516575813293},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5897959470748901},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5675206780433655},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5641345977783203},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49945569038391113},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4834931194782257},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4710181653499603},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4603431522846222},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4303123950958252},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22559800744056702},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.22128349542617798},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20501551032066345},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv45572.2020.9093385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","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":78,"referenced_works":["https://openalex.org/W2966661","https://openalex.org/W252252322","https://openalex.org/W603908379","https://openalex.org/W1518641734","https://openalex.org/W1800922288","https://openalex.org/W1836465849","https://openalex.org/W1960289438","https://openalex.org/W1994197834","https://openalex.org/W2045798786","https://openalex.org/W2060487744","https://openalex.org/W2097117768","https://openalex.org/W2104290444","https://openalex.org/W2113656553","https://openalex.org/W2117876524","https://openalex.org/W2173498666","https://openalex.org/W2194775991","https://openalex.org/W2279221249","https://openalex.org/W2294059674","https://openalex.org/W2340427832","https://openalex.org/W2401231614","https://openalex.org/W2406474429","https://openalex.org/W2408279554","https://openalex.org/W2414711238","https://openalex.org/W2520774990","https://openalex.org/W2527276685","https://openalex.org/W2558748708","https://openalex.org/W2565639579","https://openalex.org/W2569680626","https://openalex.org/W2576915720","https://openalex.org/W2601450892","https://openalex.org/W2601564443","https://openalex.org/W2610691757","https://openalex.org/W2764024122","https://openalex.org/W2768755822","https://openalex.org/W2769152880","https://openalex.org/W2769449302","https://openalex.org/W2773986597","https://openalex.org/W2778955544","https://openalex.org/W2785994986","https://openalex.org/W2889731659","https://openalex.org/W2891122218","https://openalex.org/W2895230054","https://openalex.org/W2950014519","https://openalex.org/W2953133772","https://openalex.org/W2963056148","https://openalex.org/W2963299736","https://openalex.org/W2963414638","https://openalex.org/W2963703618","https://openalex.org/W2963840672","https://openalex.org/W2963904364","https://openalex.org/W2963975324","https://openalex.org/W2964118342","https://openalex.org/W2964137095","https://openalex.org/W2997701990","https://openalex.org/W4297688279","https://openalex.org/W6600115225","https://openalex.org/W6609555574","https://openalex.org/W6618372016","https://openalex.org/W6638238755","https://openalex.org/W6638667902","https://openalex.org/W6675747103","https://openalex.org/W6685482520","https://openalex.org/W6694954494","https://openalex.org/W6696085341","https://openalex.org/W6696761078","https://openalex.org/W6713596413","https://openalex.org/W6714181750","https://openalex.org/W6716109767","https://openalex.org/W6726946684","https://openalex.org/W6727577265","https://openalex.org/W6735236233","https://openalex.org/W6743446608","https://openalex.org/W6745447533","https://openalex.org/W6745991264","https://openalex.org/W6746923874","https://openalex.org/W6748053814","https://openalex.org/W6754302822","https://openalex.org/W6842324833"],"related_works":["https://openalex.org/W4388311650","https://openalex.org/W5922282","https://openalex.org/W1974056099","https://openalex.org/W4245343541","https://openalex.org/W2386077341","https://openalex.org/W563589758","https://openalex.org/W62490179","https://openalex.org/W2954004777","https://openalex.org/W2951102138","https://openalex.org/W1568403290"],"abstract_inverted_index":{"In":[0,66],"this":[1,67],"paper":[2],"we":[3,34,69,85],"propose":[4,35],"integrating":[5],"a":[6,36,46],"priori":[7],"knowledge":[8,89],"into":[9],"both":[10],"design":[11],"and":[12,41,81,99,112],"training":[13,76],"of":[14,101,133],"convolutional":[15],"neural":[16],"networks":[17],"(CNNs)":[18],"to":[19,26,53,62,71],"learn":[20],"object":[21],"representations":[22],"that":[23,87,125],"are":[24],"invariant":[25],"affine":[27,73],"transformations":[28,74],"(i.e.":[29],"translation,":[30],"scale,":[31],"rotation).":[32],"Accordingly":[33],"novel":[37,47],"multi-scale":[38,79],"maxout":[39],"CNN":[40],"train":[42],"it":[43],"end-to-end":[44],"with":[45,114],"rotation-invariant":[48],"regularizer.":[49],"This":[50],"regularizer":[51],"aims":[52],"enforce":[54],"the":[55,93,107,127],"weights":[56],"in":[57,75,131],"each":[58],"2D":[59],"spatial":[60],"filter":[61],"approximate":[63],"circular":[64,82],"patterns.":[65],"way,":[68],"manage":[70],"handle":[72],"using":[77],"convolution,":[78],"maxout,":[80],"filters.":[83],"Empirically":[84],"demonstrate":[86],"such":[88],"can":[90,122],"significantly":[91],"improve":[92],"data-efficiency":[94],"as":[95,97],"well":[96],"generalization":[98],"robustness":[100],"learned":[102],"models.":[103],"For":[104],"instance,":[105],"on":[106],"Traffic":[108],"Sign":[109],"data":[110],"set":[111],"trained":[113],"only":[115],"10":[116],"images":[117],"per":[118],"class,":[119],"our":[120],"method":[121],"achieve":[123],"84.15%":[124],"outperforms":[126],"state-of-the-art":[128],"by":[129],"29.80%":[130],"terms":[132],"test":[134],"accuracy.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}