{"id":"https://openalex.org/W3000831883","doi":"https://doi.org/10.1109/icassp40776.2020.9053898","title":"Depthwise-STFT Based Separable Convolutional Neural Networks","display_name":"Depthwise-STFT Based Separable Convolutional Neural Networks","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3000831883","doi":"https://doi.org/10.1109/icassp40776.2020.9053898","mag":"3000831883"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.09912","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061474465","display_name":"Sudhakar Kumawat","orcid":"https://orcid.org/0000-0002-6057-2276"},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sudhakar Kumawat","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology Gandhinagar, India","Indian Institute of Technology Gandhinagar,Computer Science and Engineering,India"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Gandhinagar, India","institution_ids":["https://openalex.org/I27674431"]},{"raw_affiliation_string":"Indian Institute of Technology Gandhinagar,Computer Science and Engineering,India","institution_ids":["https://openalex.org/I27674431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070142969","display_name":"Shanmuganathan Raman","orcid":"https://orcid.org/0000-0003-2718-7891"},"institutions":[{"id":"https://openalex.org/I27674431","display_name":"Indian Institute of Technology Gandhinagar","ror":"https://ror.org/0036p5w23","country_code":"IN","type":"education","lineage":["https://openalex.org/I27674431"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shanmuganathan Raman","raw_affiliation_strings":["Computer Science and Engineering, Indian Institute of Technology Gandhinagar, India","Indian Institute of Technology Gandhinagar"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Indian Institute of Technology Gandhinagar, India","institution_ids":["https://openalex.org/I27674431"]},{"raw_affiliation_string":"Indian Institute of Technology Gandhinagar","institution_ids":["https://openalex.org/I27674431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061474465"],"corresponding_institution_ids":["https://openalex.org/I27674431"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00915013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9980999827384949,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9980999827384949,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9945999979972839,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9943000078201294,"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/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.8144739866256714},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.7060087323188782},{"id":"https://openalex.org/keywords/separable-space","display_name":"Separable space","score":0.6927645802497864},{"id":"https://openalex.org/keywords/pointwise","display_name":"Pointwise","score":0.6783674955368042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6064877510070801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6051238179206848},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.57923424243927},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5788246393203735},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5406302213668823},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5381667613983154},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5266266465187073},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5244953036308289},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5002717971801758},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34943538904190063},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.26336491107940674},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.25175660848617554},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.10228696465492249}],"concepts":[{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.8144739866256714},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.7060087323188782},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.6927645802497864},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.6783674955368042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6064877510070801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6051238179206848},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.57923424243927},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5788246393203735},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5406302213668823},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5381667613983154},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5266266465187073},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5244953036308289},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5002717971801758},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34943538904190063},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26336491107940674},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.25175660848617554},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.10228696465492249},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053898","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.09912","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.09912","pdf_url":"https://arxiv.org/pdf/2001.09912","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:3000831883","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2001.09912.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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},{"id":"doi:10.48550/arxiv.2001.09912","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.09912","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.09912","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.09912","pdf_url":"https://arxiv.org/pdf/2001.09912","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3000831883.pdf","grobid_xml":"https://content.openalex.org/works/W3000831883.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1901129140","https://openalex.org/W2194775991","https://openalex.org/W2274287116","https://openalex.org/W2531409750","https://openalex.org/W2612445135","https://openalex.org/W2883780447","https://openalex.org/W2930709109","https://openalex.org/W2937515235","https://openalex.org/W2962772649","https://openalex.org/W2962971773","https://openalex.org/W2963125010","https://openalex.org/W2963163009","https://openalex.org/W2963418739","https://openalex.org/W2963702144","https://openalex.org/W2964121744","https://openalex.org/W2964137095","https://openalex.org/W2964350391","https://openalex.org/W3118608800","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6639824700","https://openalex.org/W6713132643","https://openalex.org/W6728184133","https://openalex.org/W6737664043","https://openalex.org/W6749046737","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W3016221831","https://openalex.org/W2798727000","https://openalex.org/W3164713272","https://openalex.org/W2472130157","https://openalex.org/W2889738717","https://openalex.org/W2982098670","https://openalex.org/W3085746042","https://openalex.org/W2961374320","https://openalex.org/W2890937389","https://openalex.org/W1974667023","https://openalex.org/W3203623872","https://openalex.org/W3199917751","https://openalex.org/W2386205275","https://openalex.org/W3020692291","https://openalex.org/W2067307048","https://openalex.org/W3182818194","https://openalex.org/W1561314634","https://openalex.org/W2139646885","https://openalex.org/W2291102274","https://openalex.org/W3197341760"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5],"new":[6],"convolutional":[7,24],"layer":[8,12,31,125],"called":[9],"Depthwise-STFT":[10],"Separable":[11],"that":[13,37,122],"can":[14,41],"serve":[15],"as":[16,47],"an":[17,50],"alternative":[18],"to":[19,73],"the":[20,29,35,38,54,60,70,75,97,123,127,134],"standard":[21,128],"depthwise":[22,129],"separable":[23,130],"layer.":[25],"The":[26,78],"construction":[27],"of":[28,66,69],"proposed":[30,124],"is":[32],"inspired":[33],"by":[34],"fact":[36],"Fourier":[39,55,79,87],"coefficients":[40,56,80],"accurately":[42],"represent":[43],"important":[44],"features":[45],"such":[46],"edges":[48],"in":[49,59,96],"image.":[51],"It":[52],"utilizes":[53],"computed":[57,82],"(channelwise)":[58],"2D":[61,84,98],"local":[62,99],"neighborhood":[63,100],"(e.g.,":[64],"3x3)":[65],"each":[67,102],"position":[68],"input":[71],"map":[72],"obtain":[74],"feature":[76,105],"maps.":[77],"are":[81,111],"using":[83,115],"Short":[85],"Term":[86],"Transform":[88],"(STFT)":[89],"at":[90,101,107],"multiple":[91],"fixed":[92],"low":[93],"frequency":[94,109],"points":[95,110],"position.":[103],"These":[104],"maps":[106],"different":[108],"then":[112],"linearly":[113],"combined":[114],"trainable":[116],"pointwise":[117],"(1x1)":[118],"convolutions.":[119],"We":[120],"show":[121],"outperforms":[126],"layer-based":[131],"models":[132],"on":[133],"CIFAR-10":[135],"and":[136],"CIFAR-100":[137],"image":[138],"classification":[139],"datasets":[140],"with":[141],"reduced":[142],"space-time":[143],"complexity.":[144]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}