{"id":"https://openalex.org/W4292794346","doi":"https://doi.org/10.1109/icmew56448.2022.9859497","title":"Augmented-Training-Aware Bisenet for Real-Time Semantic Segmentation","display_name":"Augmented-Training-Aware Bisenet for Real-Time Semantic Segmentation","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4292794346","doi":"https://doi.org/10.1109/icmew56448.2022.9859497"},"language":"en","primary_location":{"id":"doi:10.1109/icmew56448.2022.9859497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew56448.2022.9859497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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/A5007305393","display_name":"Chih\u2013Chung Hsu","orcid":"https://orcid.org/0000-0002-2083-4438"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chih-Chung Hsu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035108154","display_name":"Cheih Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheih Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032444776","display_name":"Shen-Chieh Tai","orcid":"https://orcid.org/0000-0001-7115-4646"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen-Chieh Tai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019965181","display_name":"Yunzhong Jiang","orcid":"https://orcid.org/0000-0001-8018-8346"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun-Zhong Jiang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007305393"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07396847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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":0.996399998664856,"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":0.9879999756813049,"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":0.8234429359436035},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7774637937545776},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7736638784408569},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6670349836349487},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6145200729370117},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5314143300056458},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5288112163543701},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.499436616897583},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.43704622983932495},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43521246314048767},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4310925006866455},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.41282832622528076},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36372238397598267},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34562212228775024},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.329932302236557},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10991564393043518}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8234429359436035},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7774637937545776},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7736638784408569},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6670349836349487},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6145200729370117},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5314143300056458},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5288112163543701},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.499436616897583},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.43704622983932495},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43521246314048767},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4310925006866455},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.41282832622528076},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36372238397598267},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34562212228775024},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.329932302236557},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10991564393043518}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmew56448.2022.9859497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew56448.2022.9859497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2886934227","https://openalex.org/W2899771611","https://openalex.org/W2916798096","https://openalex.org/W2963420686","https://openalex.org/W2964309882","https://openalex.org/W2990229957","https://openalex.org/W3034958977","https://openalex.org/W3109301572","https://openalex.org/W3159637683","https://openalex.org/W3169865585","https://openalex.org/W3171398643","https://openalex.org/W4224920174","https://openalex.org/W6639824700","https://openalex.org/W6743731764","https://openalex.org/W6748481559","https://openalex.org/W6756040250","https://openalex.org/W6770971415","https://openalex.org/W6794556019","https://openalex.org/W6810938606"],"related_works":["https://openalex.org/W2185902295","https://openalex.org/W2103507220","https://openalex.org/W3144569342","https://openalex.org/W2945274617","https://openalex.org/W4313052709","https://openalex.org/W4205800335","https://openalex.org/W2022929107","https://openalex.org/W2055202857","https://openalex.org/W80586315","https://openalex.org/W2758994127"],"abstract_inverted_index":{"Semantic":[0],"segmentation":[1,24,39,53,95],"techniques":[2],"have":[3],"become":[4],"an":[5,79,86],"attractive":[6],"research":[7],"field":[8],"for":[9,40,176],"autonomous":[10,41,177],"driving.":[11],"However,":[12,61],"it":[13],"is":[14,25,43,56,68,111,149,172],"well-known":[15],"that":[16,72,168],"the":[17,21,37,51,62,65,73,93,114,119,122,127,137,142,147,152,158,169],"computational":[18,162],"complexity":[19],"of":[20,36,64,121],"conventional":[22,66],"semantic":[23,38,94],"relatively":[26],"high":[27],"compared":[28],"to":[29,78,90,117,140,155],"other":[30,181],"computer":[31],"vision":[32],"applications.":[33],"Fast":[34],"inference":[35],"driving":[42,178],"highly":[44],"desired.":[45],"A":[46],"lightweight":[47],"convolutional":[48],"neural":[49],"network,":[50],"Bilateral":[52],"network":[54],"(BiSeNet),":[55],"adopted":[57],"in":[58,113,136],"this":[59],"paper.":[60],"performance":[63,120],"BiSeNet":[67],"not":[69],"so":[70],"reliable":[71],"model":[74,138,154,159],"quantization":[75],"could":[76],"lead":[77],"even":[80],"worse":[81],"result.":[82],"Therefore,":[83],"we":[84],"proposed":[85,170],"augmented":[87],"training":[88,115,139],"strategy":[89],"significantly":[91,156],"improve":[92],"task\u2019s":[96],"performance.":[97],"First,":[98],"heavy":[99],"data":[100],"augmentation,":[101],"including":[102],"CutOut,":[103],"deformable":[104],"distortion,":[105],"and":[106,129,161,174],"step-wise":[107],"hard":[108],"example":[109],"mining,":[110],"used":[112,135],"phase":[116],"boost":[118],"feature":[123],"representation":[124],"learning.":[125],"Second,":[126],"L1":[128],"L2":[130],"norm":[131],"regularization":[132],"are":[133],"also":[134],"prevent":[141],"possible":[143],"overfitting":[144],"issue.":[145],"Then,":[146],"post-quantization":[148],"performed":[150],"on":[151],"TensorFlow-Lite":[153],"reduce":[157],"size":[160],"complexity.":[163],"The":[164],"comprehensive":[165],"experiments":[166],"verified":[167],"method":[171],"effective":[173],"efficient":[175],"applications":[179],"over":[180],"state-of-the-art":[182],"methods.":[183]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}