{"id":"https://openalex.org/W6990076860","doi":null,"title":"Convolutional Neural Networks based on Discrete Cosine Transform with Applications in Computer Vision","display_name":"Convolutional Neural Networks based on Discrete Cosine Transform with Applications in Computer Vision","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W6990076860"},"language":"en","primary_location":{"id":"pmh:http://www.rian.ie/195815/","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2262/96207","pdf_url":"http://hdl.handle.net/2262/96207","source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210144925","host_organization_name":"Technological University Dublin","host_organization_lineage":["https://openalex.org/I4210144925"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ulicny, Matej, Convolutional Neural Networks based on Discrete Cosine Transform with Applications in Computer Vision, Trinity College Dublin.School of Computer Science & Statistics, 2021","raw_type":"Doctoral thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2262/96207","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051741436","display_name":"Matej Uli\u010dn\u00fd","orcid":"https://orcid.org/0000-0003-4490-0492","observed_orcids":["https://orcid.org/0000-0003-4490-0492"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ulicny, Matej","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5051741436"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network 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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network 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"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.0010000000474974513,"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":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"discrete cosine transform","score":0.8679999709129333},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.9490000009536743},{"id":"https://openalex.org/keywords/weight-regularization","display_name":"weight regularization","score":0.6930000185966492},{"id":"https://openalex.org/keywords/model-compression","display_name":"model compression","score":0.7080000042915344},{"id":"https://openalex.org/keywords/illumination-invariance","display_name":"illumination invariance","score":0.8180000185966492},{"id":"https://openalex.org/keywords/batch-normalization","display_name":"batch normalization","score":0.44999998807907104},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.5139999985694885},{"id":"https://openalex.org/keywords/object-detection","display_name":"object detection","score":0.9990000128746033},{"id":"https://openalex.org/keywords/semantic-segmentation","display_name":"semantic segmentation","score":0.9409999847412109},{"id":"https://openalex.org/keywords/overfitting","display_name":"overfitting","score":0.6359999775886536}],"concepts":[{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.8284000158309937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896999716758728},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6847000122070312},{"id":"https://openalex.org/C198751489","wikidata":"https://www.wikidata.org/wiki/Q2195","display_name":"JPEG","level":3,"score":0.6754000186920166},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.638700008392334},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.5270000100135803},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.51419997215271},{"id":"https://openalex.org/C69216139","wikidata":"https://www.wikidata.org/wiki/Q931783","display_name":"JPEG 2000","level":5,"score":0.4855000078678131},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.474700003862381},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46889999508857727},{"id":"https://openalex.org/C75608658","wikidata":"https://www.wikidata.org/wiki/Q44395","display_name":"Pascal (unit)","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.4212999939918518},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3366999924182892},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.32179999351501465},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.30550000071525574},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.25920000672340393}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:http://www.rian.ie/195815/","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2262/96207","pdf_url":"http://hdl.handle.net/2262/96207","source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210144925","host_organization_name":"Technological University Dublin","host_organization_lineage":["https://openalex.org/I4210144925"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ulicny, Matej, Convolutional Neural Networks based on Discrete Cosine Transform with Applications in Computer Vision, Trinity College Dublin.School of Computer Science & Statistics, 2021","raw_type":"Doctoral thesis"},{"id":"pmh:oai:tara.tcd.ie:2262/96207","doi":null,"is_oa":false,"landing_page_url":"https://tcdlocalportal.tcd.ie/pls/EnterApex/f?p=800:71:0::::P71_USERNAME:ULINM","pdf_url":null,"source":{"id":"https://openalex.org/S4306400387","display_name":"Trinity's Access to Research Output (TARA) (Trinity College Dublin)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205274468","host_organization_name":"Trinity College Dublin","host_organization_lineage":["https://openalex.org/I205274468"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:http://www.rian.ie/195815/","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2262/96207","pdf_url":"http://hdl.handle.net/2262/96207","source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210144925","host_organization_name":"Technological University Dublin","host_organization_lineage":["https://openalex.org/I4210144925"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ulicny, Matej, Convolutional Neural Networks based on Discrete Cosine Transform with Applications in Computer Vision, Trinity College Dublin.School of Computer Science & Statistics, 2021","raw_type":"Doctoral thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6990076860.pdf","grobid_xml":"https://content.openalex.org/works/W6990076860.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W613766092","https://openalex.org/W1498436455","https://openalex.org/W1509715878","https://openalex.org/W1836465849","https://openalex.org/W1929963669","https://openalex.org/W1989085630","https://openalex.org/W1995341919","https://openalex.org/W2027735369","https://openalex.org/W2031614119","https://openalex.org/W2040870580","https://openalex.org/W2066477856","https://openalex.org/W2104058988","https://openalex.org/W2108598243","https://openalex.org/W2110158442","https://openalex.org/W2137983211","https://openalex.org/W2140582552","https://openalex.org/W2147800946","https://openalex.org/W2165550102","https://openalex.org/W2168162153","https://openalex.org/W2621199038","https://openalex.org/W2630837129","https://openalex.org/W2737081839","https://openalex.org/W2746314669","https://openalex.org/W2884013187","https://openalex.org/W2915589364","https://openalex.org/W2934088140","https://openalex.org/W2943827948","https://openalex.org/W2950141105","https://openalex.org/W2953350231","https://openalex.org/W2963420686","https://openalex.org/W2963849369","https://openalex.org/W2964121744","https://openalex.org/W2996074092","https://openalex.org/W2998508940","https://openalex.org/W3034251466","https://openalex.org/W4394670654"],"related_works":["https://openalex.org/W2891364477","https://openalex.org/W3001834601","https://openalex.org/W3149156336","https://openalex.org/W4406559840","https://openalex.org/W4224299186","https://openalex.org/W2966733620","https://openalex.org/W3011628663","https://openalex.org/W2609675817","https://openalex.org/W4211206257","https://openalex.org/W2783569857"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1,260],"networks":[2],"(CNNs)":[3],"have":[4],"become":[5],"a":[6,19,101,211,224,266,269,331,339,354],"paradigm":[7],"for":[8,333],"designing":[9],"vision":[10],"based":[11,276],"intelligent":[12],"systems.":[13],"These":[14],"models":[15,136,193,348],"are":[16,25,241,302,327],"controlled":[17],"by":[18,145,153,162,172],"vast":[20],"amount":[21],"of":[22,31,66,72,100,169,176,312,321,338,342],"parameters,":[23],"which":[24],"learned":[26],"thanks":[27],"to":[28,50,60,78,88,93,166,195,251,254,264,285,316,347],"the":[29,67,76,113,130,174,181,184,188,220,243,281,287,307,322],"availability":[30],"annotated":[32],"datasets.":[33],"Image":[34],"data":[35],"is":[36,232,247,294],"available":[37],"in":[38,97,204,217,259,283,356],"multiple":[39,201],"formats":[40],"including":[41],"JPEG":[42,68,81],"that":[43,106,118,226],"uses":[44],"Discrete":[45],"Cosine":[46],"Transform":[47],"(DCT)":[48],"coefficients":[49,65],"efficiently":[51,209],"encode":[52],"and":[53,103,127,155,208,234,249,272,299,309],"compress":[54,210],"visual":[55],"information.":[56],"We":[57,116,132,164,262,304],"first":[58,189],"propose":[59,87,165,263],"use":[61,89,337],"directly":[62],"these":[63],"DCT":[64,90,122,221,298],"images":[69,171],"as":[70,141],"input":[71],"CNN":[73,102],"models,":[74],"removing":[75],"need":[77,332],"completely":[79],"decode":[80],"format":[82],"before":[83],"applying":[84],"CNNs.\\nFurthermore,":[85],"we":[86,104],"basis":[91,177],"functions":[92,178],"express":[94],"convolutional":[95],"filters":[96],"any":[98,214,255],"layer":[99,190],"show":[105,117],"this":[107],"provides":[108,223],"an":[109],"advantageous":[110],"regularization":[111],"during":[112,180],"training":[114],"process.":[115],"expressing":[119],"weights":[120],"within":[121],"bases":[123,222],"can":[124,191,203,345],"increase":[125],"performance":[126],"speed":[128],"up":[129],"training.":[131,182],"improve":[133],"several":[134],"popular":[135],"on":[137,187,200,277],"standard":[138,244],"benchmarks":[139],"such":[140],"ImageNet":[142],"classification":[143],"accuracy":[144],"1%,":[146],"MS":[147],"COCO":[148],"object":[149],"detection":[150],"average":[151],"precision":[152],"1%":[154],"Pascal":[156],"VOC":[157],"semantic":[158],"segmentation":[159],"IoU":[160],"score":[161],"1.1%.":[163],"exploit":[167],"properties":[168],"natural":[170],"restricting":[173],"set":[175],"used":[179,258],"Suppressing":[183],"low-frequency":[185],"component":[186],"make":[192,286],"insensitive":[194],"illumination":[196],"effects.":[197],"High-frequency":[198],"truncation":[199],"layers":[202,315],"turn":[205],"add":[206],"stability":[207],"model":[212,334],"without":[213,330,353],"significant":[215],"loss":[216,355],"accuracy.":[218,357],"Using":[219],"prior":[225],"reduces":[227],"overfitting,":[228],"specially":[229],"when":[230,238],"compression":[231,246,320],"applied,":[233],"helps":[235],"with":[236,349],"generalization":[237],"fewer":[239,351],"samples":[240],"available.\\nLastly,":[242],"DCT-based":[245],"modified":[248],"extended":[250],"be":[252],"applicable":[253],"weight":[256],"tensor":[257,267],"networks.":[261],"reshape":[265],"into":[268,318],"2-dimensional":[270],"matrix":[271,288,293],"reorder":[273],"its":[274],"rows":[275],"pairwise":[278],"distances":[279],"between":[280],"columns":[282],"order":[284],"more":[289],"coherent.":[290],"The":[291,336],"reordered":[292],"transformed":[295],"via":[296],"1-dimensional":[297],"high":[300],"frequencies":[301],"truncated.":[303],"further":[305],"correct":[306],"scale":[308],"bias":[310],"parameters":[311,352],"batch":[313],"normalization":[314],"take":[317],"account":[319],"preceding":[323],"layers.":[324],"Promising":[325],"results":[326],"achieved":[328],"even":[329],"fine-tuning.":[335],"short":[340],"fine-tuning":[341],"one":[343],"epoch":[344],"lead":[346],"3-times":[350]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}