{"id":"https://openalex.org/W4312235855","doi":"https://doi.org/10.1109/mlsp55214.2022.9943334","title":"SVIT: Hybrid Vision Transformer Models with Scattering Transform","display_name":"SVIT: Hybrid Vision Transformer Models with Scattering Transform","publication_year":2022,"publication_date":"2022-08-22","ids":{"openalex":"https://openalex.org/W4312235855","doi":"https://doi.org/10.1109/mlsp55214.2022.9943334"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp55214.2022.9943334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp55214.2022.9943334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 32nd International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5027090002","display_name":"Tianming Qiu","orcid":"https://orcid.org/0000-0003-1089-4717"},"institutions":[{"id":"https://openalex.org/I4210134795","display_name":"Fortiss","ror":"https://ror.org/042x1tp92","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210134795"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tianming Qiu","raw_affiliation_strings":["fortiss GmbH,Munich,Germany","fortiss GmbH, Munich, Germany","Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"fortiss GmbH,Munich,Germany","institution_ids":["https://openalex.org/I4210134795"]},{"raw_affiliation_string":"fortiss GmbH, Munich, Germany","institution_ids":["https://openalex.org/I4210134795"]},{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044990873","display_name":"Ming Gui","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ming Gui","raw_affiliation_strings":["Technical University of Munich,Munich,Germany","Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100613014","display_name":"Cheng Yan","orcid":"https://orcid.org/0000-0002-5021-6841"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cheng Yan","raw_affiliation_strings":["Technical University of Munich,Munich,Germany","Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033027820","display_name":"Ziqing Zhao","orcid":"https://orcid.org/0000-0002-1233-9867"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ziqing Zhao","raw_affiliation_strings":["Technical University of Munich,Munich,Germany","Technical University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Munich,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101759953","display_name":"Hao Shen","orcid":"https://orcid.org/0000-0003-0091-4155"},"institutions":[{"id":"https://openalex.org/I4210134795","display_name":"Fortiss","ror":"https://ror.org/042x1tp92","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4210134795"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hao Shen","raw_affiliation_strings":["fortiss GmbH,Munich,Germany","Technical University of Munich, Munich, Germany","fortiss GmbH, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"fortiss GmbH,Munich,Germany","institution_ids":["https://openalex.org/I4210134795"]},{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"fortiss GmbH, Munich, Germany","institution_ids":["https://openalex.org/I4210134795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"01","last_page":"06"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9997000098228455,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9988999962806702,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.7363046407699585},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7106402516365051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6312575936317444},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44144514203071594},{"id":"https://openalex.org/keywords/scattering","display_name":"Scattering","score":0.4369843006134033},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43068134784698486},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.41656485199928284},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3768945336341858},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3388494849205017},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11993712186813354},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08965209126472473},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.08837246894836426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7363046407699585},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7106402516365051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6312575936317444},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44144514203071594},{"id":"https://openalex.org/C191486275","wikidata":"https://www.wikidata.org/wiki/Q210028","display_name":"Scattering","level":2,"score":0.4369843006134033},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43068134784698486},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.41656485199928284},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3768945336341858},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3388494849205017},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11993712186813354},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08965209126472473},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.08837246894836426},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp55214.2022.9943334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp55214.2022.9943334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 32nd International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1677409904","https://openalex.org/W1932922755","https://openalex.org/W1994906459","https://openalex.org/W2072072671","https://openalex.org/W2118858186","https://openalex.org/W2124386111","https://openalex.org/W2163605009","https://openalex.org/W2400151227","https://openalex.org/W2533598788","https://openalex.org/W2601564443","https://openalex.org/W2884013187","https://openalex.org/W2963840672","https://openalex.org/W2964194231","https://openalex.org/W3094502228","https://openalex.org/W3121523901","https://openalex.org/W3136416617","https://openalex.org/W3156811085","https://openalex.org/W3159778524","https://openalex.org/W3171087525","https://openalex.org/W4214493665","https://openalex.org/W4299802238","https://openalex.org/W4385245566","https://openalex.org/W6640425500","https://openalex.org/W6677919164","https://openalex.org/W6678135826","https://openalex.org/W6684191040","https://openalex.org/W6696085341","https://openalex.org/W6728588997","https://openalex.org/W6739901393","https://openalex.org/W6769955919","https://openalex.org/W6784333009","https://openalex.org/W6794906783","https://openalex.org/W6795062860","https://openalex.org/W6796931752"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W4391266461","https://openalex.org/W2590798552","https://openalex.org/W2811106690","https://openalex.org/W4239306820","https://openalex.org/W2947043951","https://openalex.org/W4399188509","https://openalex.org/W4312417841"],"abstract_inverted_index":{"Transformer":[0,60,96],"architectures":[1],"not":[2],"only":[3],"enable":[4],"significant":[5],"performance":[6,109],"in":[7,23,29,43],"natural":[8],"language":[9],"processing":[10],"tasks,":[11],"but":[12],"also":[13],"demon-strate":[14],"comparable":[15],"feature":[16],"extraction":[17],"ability":[18],"as":[19,121],"convolutional":[20],"neural":[21],"networks":[22],"computer":[24],"vision":[25],"tasks.":[26],"Unlike":[27],"words":[28],"sentences,":[30],"it":[31],"is":[32,75],"difficult":[33],"to":[34],"specify":[35],"a":[36,65],"graphic":[37],"token":[38],"with":[39,90],"definite":[40],"semantic":[41],"representations":[42],"pictures,":[44],"which":[45],"diminishes":[46],"the":[47,50],"impact":[48],"of":[49,77,110],"self-attention":[51],"mechanism.":[52],"This":[53],"work":[54],"inves-tigates":[55],"tokenization":[56],"methods":[57],"for":[58],"Vision":[59,95],"(ViT).":[61],"Scattering":[62],"transform":[63,92],"shares":[64],"tiny":[66],"network":[67],"structure":[68],"based":[69],"on":[70,99,114],"fixed":[71],"wavelet":[72],"filters.":[73],"It":[74],"capable":[76],"providing":[78],"adequate":[79],"spatial":[80],"and":[81],"frequency-based":[82],"tokenizations.":[83],"So":[84],"we":[85],"propose":[86],"hybrid":[87],"ViT":[88],"models":[89],"scattering":[91],"called":[93],"Scat-tering":[94],"(SViT).":[97],"Experiments":[98],"image":[100,123],"classification":[101],"tasks":[102,119],"suggest":[103],"that":[104],"scattering-transform-based":[105],"tokenizations":[106],"can":[107],"improve":[108],"vanilla":[111],"ViT,":[112],"especially":[113],"small":[115],"datasets":[116],"or":[117],"frequency-sensitive":[118],"such":[120],"satellite":[122],"classification.":[124],"Our":[125],"codes":[126],"are":[127],"available":[128],"at":[129],"https://github.com/TianmingQiu/scattering_transformer.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}