{"id":"https://openalex.org/W2885271594","doi":"https://doi.org/10.23919/mixdes.2018.8436926","title":"Learning Robust Feature Representations in Deep Networks for Image Classification","display_name":"Learning Robust Feature Representations in Deep Networks for Image Classification","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2885271594","doi":"https://doi.org/10.23919/mixdes.2018.8436926","mag":"2885271594"},"language":"en","primary_location":{"id":"doi:10.23919/mixdes.2018.8436926","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mixdes.2018.8436926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 25th International Conference \"Mixed Design of Integrated Circuits and System\" (MIXDES)","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/A5007268186","display_name":"Breton Minnehan","orcid":"https://orcid.org/0000-0001-7997-1210"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Breton Minnehan","raw_affiliation_strings":["Rochester Institute of Technology, Rochester, New York, USA"],"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, New York, USA","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022041853","display_name":"Andreas Savakis","orcid":"https://orcid.org/0000-0002-9657-3027"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Savakis","raw_affiliation_strings":["Rochester Institute of Technology, Rochester, New York, USA"],"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology, Rochester, New York, USA","institution_ids":["https://openalex.org/I155173764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007268186"],"corresponding_institution_ids":["https://openalex.org/I155173764"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08004772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9991999864578247,"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/hyperparameter","display_name":"Hyperparameter","score":0.7358242273330688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7177280783653259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6998230814933777},{"id":"https://openalex.org/keywords/silhouette","display_name":"Silhouette","score":0.6697654724121094},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6252886056900024},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5848811864852905},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.5550315380096436},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.538456380367279},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5364262461662292},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5282708406448364},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4644840359687805},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4567112326622009},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.44133108854293823},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2363736927509308},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1730981171131134}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7358242273330688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7177280783653259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6998230814933777},{"id":"https://openalex.org/C58103923","wikidata":"https://www.wikidata.org/wiki/Q2286025","display_name":"Silhouette","level":2,"score":0.6697654724121094},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6252886056900024},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5848811864852905},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.5550315380096436},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.538456380367279},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5364262461662292},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5282708406448364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4644840359687805},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4567112326622009},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.44133108854293823},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2363736927509308},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1730981171131134},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/mixdes.2018.8436926","is_oa":false,"landing_page_url":"https://doi.org/10.23919/mixdes.2018.8436926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 25th International Conference \"Mixed Design of Integrated Circuits and System\" (MIXDES)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1731081199","https://openalex.org/W1836465849","https://openalex.org/W1882958252","https://openalex.org/W1987971958","https://openalex.org/W2095705004","https://openalex.org/W2096733369","https://openalex.org/W2097117768","https://openalex.org/W2100659887","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2156387975","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2279098554","https://openalex.org/W2335728318","https://openalex.org/W2520774990","https://openalex.org/W2750384547","https://openalex.org/W2962835968","https://openalex.org/W2963430102","https://openalex.org/W2963446712","https://openalex.org/W2963826681","https://openalex.org/W2964054038","https://openalex.org/W3099206234","https://openalex.org/W6637373629","https://openalex.org/W6637618735","https://openalex.org/W6674330103","https://openalex.org/W6682889407","https://openalex.org/W6703116779","https://openalex.org/W6726946684"],"related_works":["https://openalex.org/W1622964048","https://openalex.org/W30315714","https://openalex.org/W1965274140","https://openalex.org/W779885325","https://openalex.org/W2150972844","https://openalex.org/W2393615320","https://openalex.org/W3110435694","https://openalex.org/W2001760863","https://openalex.org/W2185145003","https://openalex.org/W4313435806"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"has":[2],"emerged":[3],"as":[4,25],"the":[5,18,38,46,64,74,88,92,100],"method":[6],"of":[7,20,48,76,91,102,123],"choice":[8],"for":[9,41,66,73,87],"many":[10],"computer":[11],"vision":[12],"applications.":[13],"Training":[14],"deep":[15,43],"networks":[16,44],"involves":[17],"utilization":[19],"a":[21,33,107],"loss":[22,36,113],"function,":[23,37],"such":[24],"cross":[26],"entropy.":[27],"In":[28],"this":[29],"paper,":[30],"we":[31,114],"propose":[32],"novel":[34],"auxiliary":[35,93,112],"Silhouette":[39],"Loss,":[40],"training":[42,106],"with":[45,110],"objective":[47],"obtaining":[49],"feature":[50],"representations":[51],"that":[52,69,118,122],"are":[53,61],"both":[54],"tightly":[55],"clustered":[56],"and":[57,98,132],"highly":[58],"separable.":[59],"We":[60,80],"motivated":[62],"by":[63],"need":[65],"well-clustered":[67],"features":[68],"can":[70],"generalize":[71],"effectively":[72],"classification":[75,116],"diverse":[77],"test":[78],"samples.":[79],"also":[81],"introduce":[82],"an":[83],"adaptive":[84],"scaling":[85],"scheme":[86],"regularization":[89],"parameter":[90],"loss,":[94],"which":[95],"improves":[96],"robustness":[97],"eliminates":[99],"selection":[101],"another":[103],"hyperparameter.":[104],"By":[105],"small":[108],"network":[109,128],"our":[111,127],"achieve":[115],"performance":[117],"is":[119,129],"comparable":[120],"to":[121],"larger":[124],"networks,":[125],"yet":[126],"more":[130],"efficient":[131],"utilizes":[133],"much":[134],"fewer":[135],"parameters.":[136]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}