{"id":"https://openalex.org/W4312599311","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892388","title":"Using CNN to improve the performance of the Light-weight ViT","display_name":"Using CNN to improve the performance of the Light-weight ViT","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312599311","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892388"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892388","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100355085","display_name":"Xiaopeng Li","orcid":"https://orcid.org/0000-0002-5479-7452"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaopeng Li","raw_affiliation_strings":["School of Information Engineering, Northwest A&F University,Xianyang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Northwest A&F University,Xianyang,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100778778","display_name":"Shuqin Li","orcid":"https://orcid.org/0000-0002-5805-6352"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuqin Li","raw_affiliation_strings":["School of Information Engineering, Northwest A&F University,Xianyang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Northwest A&F University,Xianyang,China","institution_ids":[]}]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9983999729156494,"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7354737520217896},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7228814959526062},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6439404487609863},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6096044778823853},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.552073061466217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4926953613758087},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48008328676223755},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4683152139186859},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46521806716918945},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4397790729999542},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.43700915575027466},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10886237025260925},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.099572092294693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354737520217896},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7228814959526062},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6439404487609863},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6096044778823853},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.552073061466217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4926953613758087},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48008328676223755},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4683152139186859},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46521806716918945},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4397790729999542},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.43700915575027466},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10886237025260925},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.099572092294693},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892388","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G280089375","display_name":null,"funder_award_id":"2020YFD1100600,2020YFD1100601","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W1650736245","https://openalex.org/W1686810756","https://openalex.org/W2117539524","https://openalex.org/W2147800946","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2531409750","https://openalex.org/W2549139847","https://openalex.org/W2609476118","https://openalex.org/W2622263826","https://openalex.org/W2765407302","https://openalex.org/W2883780447","https://openalex.org/W2884585870","https://openalex.org/W2922509574","https://openalex.org/W2944223741","https://openalex.org/W2946948417","https://openalex.org/W2953937638","https://openalex.org/W2955425717","https://openalex.org/W2962772649","https://openalex.org/W2963037463","https://openalex.org/W2963091558","https://openalex.org/W2963163009","https://openalex.org/W2963420686","https://openalex.org/W2963495494","https://openalex.org/W2963918968","https://openalex.org/W2982083293","https://openalex.org/W2992308087","https://openalex.org/W2998508940","https://openalex.org/W3110420020","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3137278571","https://openalex.org/W3137963805","https://openalex.org/W3138516171","https://openalex.org/W3139773203","https://openalex.org/W3156811085","https://openalex.org/W3159663321","https://openalex.org/W3170874841","https://openalex.org/W3171087525","https://openalex.org/W3172509117","https://openalex.org/W3175544090","https://openalex.org/W3190492058","https://openalex.org/W4214493665","https://openalex.org/W4214588794","https://openalex.org/W4214636423","https://openalex.org/W4214669216","https://openalex.org/W4295727797","https://openalex.org/W4297665946","https://openalex.org/W4297775537","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6638444622","https://openalex.org/W6684191040","https://openalex.org/W6737664043","https://openalex.org/W6739901393","https://openalex.org/W6751795773","https://openalex.org/W6753412334","https://openalex.org/W6757256307","https://openalex.org/W6764990469","https://openalex.org/W6779602356","https://openalex.org/W6781176803","https://openalex.org/W6788135285"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W2810679507"],"abstract_inverted_index":{"At":[0],"present,":[1],"the":[2,14,19,27,42,74,91,97,109,114,118,128,133],"Vision":[3],"Transformer":[4],"(ViT)":[5],"has":[6],"shown":[7],"excellent":[8],"performance":[9,15,134],"on":[10,65],"multiple":[11],"tasks,":[12],"but":[13],"drops":[16],"sharply":[17],"when":[18],"benchmark":[20],"ViT":[21,43,75,99],"is":[22,94],"compressed.":[23],"Experiments":[24],"show":[25,126],"that":[26,127],"first":[28],"few":[29],"layers":[30,40],"of":[31,80,135],"multi-head":[32],"attention":[33],"(MSA)":[34],"and":[35,142],"feedforward":[36],"neural":[37,67],"network":[38,68],"(FFN)":[39],"in":[41],"Block":[44],"are":[45],"not":[46],"good":[47],"at":[48],"processing":[49],"low-level":[50],"features":[51,72],"obtained":[52,83],"from":[53],"early":[54],"convolutional":[55,66],"layers.":[56],"The":[57,77],"proposed":[58,129],"Multiscale":[59],"Patch":[60],"Embedding":[61],"(MPE)":[62],"module":[63],"based":[64],"can":[69,116,131],"provide":[70,86],"higher-level":[71],"for":[73,90,113],"module.":[76],"feature":[78],"maps":[79],"different":[81],"levels":[82],"by":[84,144],"MPE":[85],"various":[87],"receptive":[88],"fields":[89],"patch,":[92],"which":[93],"beneficial":[95],"to":[96,107],"following":[98],"Blocks.":[100],"And":[101],"using":[102],"Global":[103],"Average":[104],"Pooling":[105],"(GAP)":[106],"replace":[108],"class":[110],"token":[111],"used":[112],"prediction":[115],"extract":[117],"final":[119],"output":[120],"characteristics":[121],"more":[122],"effectively.":[123],"Experimental":[124],"results":[125],"method":[130],"improve":[132],"ViT-based":[136],"light-weight":[137],"models":[138],"such":[139],"as":[140],"Swin":[141],"DeiT":[143],"2.9%-15.4%.":[145]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}