{"id":"https://openalex.org/W4412524848","doi":"https://doi.org/10.1145/3735014.3735919","title":"Enhancing Generalization in Deep Learning-Based Image Recognition under Complex Scenes","display_name":"Enhancing Generalization in Deep Learning-Based Image Recognition under Complex Scenes","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W4412524848","doi":"https://doi.org/10.1145/3735014.3735919"},"language":"en","primary_location":{"id":"doi:10.1145/3735014.3735919","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3735014.3735919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Big Data Mining and Information Processing","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":null,"display_name":"Jing Gao","orcid":"https://orcid.org/0009-0004-5521-6308"},"institutions":[{"id":"https://openalex.org/I4210143016","display_name":"Changchun Institute of Technology","ror":"https://ror.org/03r6wam78","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210143016"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Gao","raw_affiliation_strings":["Changchun Institute of Education, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0009-0004-5521-6308","affiliations":[{"raw_affiliation_string":"Changchun Institute of Education, Changchun, Jilin, China","institution_ids":["https://openalex.org/I4210143016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115600535","display_name":"Shuhe Zhang","orcid":"https://orcid.org/0000-0002-4502-0000"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhe Zhang","raw_affiliation_strings":["College of Software, Jilin University, Changchun, Jilin, China"],"raw_orcid":"https://orcid.org/0000-0002-4502-0000","affiliations":[{"raw_affiliation_string":"College of Software, Jilin University, Changchun, Jilin, China","institution_ids":["https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210143016"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29776611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"314","last_page":"319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9966999888420105,"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":0.9966999888420105,"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":0.9955999851226807,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9955000281333923,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7185587286949158},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7182052135467529},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.690879762172699},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5470058917999268},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4462401866912842},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4436955153942108},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43412673473358154},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13800984621047974}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7185587286949158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7182052135467529},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.690879762172699},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5470058917999268},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4462401866912842},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4436955153942108},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43412673473358154},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13800984621047974},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3735014.3735919","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3735014.3735919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 International Conference on Big Data Mining and Information Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2941548848","https://openalex.org/W3007818288","https://openalex.org/W3082326062","https://openalex.org/W3125406703","https://openalex.org/W3126924608","https://openalex.org/W3173986559","https://openalex.org/W3196577932","https://openalex.org/W4296935237","https://openalex.org/W4385617112","https://openalex.org/W4385987543","https://openalex.org/W4385992970","https://openalex.org/W4388952217"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W4375867731","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W3022347918"],"abstract_inverted_index":{"As":[0],"a":[1,36],"core":[2],"technology":[3],"in":[4,33,62,118,125,128,163,176],"AI,":[5],"deep":[6,17],"learning":[7],"(DL)":[8],"can":[9,57],"automatically":[10],"learn":[11],"features":[12,43],"of":[13,89,101,142],"images":[14,63,127],"by":[15],"using":[16,112],"neural":[18],"networks":[19],"to":[20,28,81],"achieve":[21,82],"high":[22],"image":[23,30,160],"recognition":[24,31,88,135],"accuracy.":[25],"In":[26],"order":[27],"address":[29],"problems":[32],"complex":[34,129],"scenes,":[35,130],"DL":[37,158],"model":[38,56,103,132],"with":[39,105],"attention":[40,49,53,144],"and":[41,51,64,109,114,121,136,146,171],"multi-scale":[42],"is":[44],"proposed.":[45],"Incorporating":[46],"the":[47,55,59,87,99,106,131,140,143,147,157],"channel":[48],"(CA)":[50],"spatial":[52],"(SA),":[54],"target":[58],"critical":[60],"areas":[61],"depress":[65],"background":[66],"noise":[67],"as":[68,70],"well":[69],"meaningless":[71],"information.":[72],"And":[73],"it":[74],"adopts":[75],"feature":[76,84,149],"pyramid":[77],"network":[78],"(FPN)":[79],"form":[80],"multiscale":[83,148],"fusion,":[85],"enhancing":[86],"object":[90],"targets":[91],"for":[92,174],"various":[93],"scales.":[94],"The":[95],"experiment":[96],"analysis":[97],"shows":[98],"effectiveness":[100,141],"our":[102],"compared":[104],"typical":[107],"VGG":[108],"ResNet":[110],"models":[111],"CIFAR-10":[113],"ImageNet":[115],"data":[116],"sets":[117],"accuracy,":[119],"recall":[120],"F1":[122],"score.":[123],"Particularly,":[124],"processing":[126],"has":[133],"better":[134],"robustness,":[137],"which":[138],"verifies":[139],"mechanism":[145],"fusion":[150],"strategy.":[151],"Research":[152],"findings":[153],"not":[154],"only":[155],"improve":[156],"model's":[159],"identification":[161],"performance":[162],"challenging":[164],"scenes":[165],"but":[166],"also":[167],"offer":[168],"solid":[169],"theoretical":[170],"technical":[172],"justification":[173],"use":[175],"related":[177],"domains.":[178]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}