Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197264024> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3197264024 endingPage "132989" @default.
- W3197264024 startingPage "132980" @default.
- W3197264024 abstract "Deep Neural Networks (DNNs) are extensively deployed in today’s safety-critical autonomous systems thanks to their high performance. However, they are known to make mistakes unpredictably, e.g., a DNN may misclassify an object if it is used for perception, or issue unsafe control commands if it is used for planning and control. One common cause for such unpredictable mistakes is Out-of-Distribution (OOD) inputs, i.e., test inputs that fall outside of the distribution of the training dataset. In this paper, we present a framework for OOD detection based on outlier detection in the hidden layers of a DNN by applying Isolation Forest (IF) and Local Outlier Factor (LOF) techniques. Extensive experimental evaluation indicates that LOF is a promising method in terms of both the Machine Learning metrics of precision, recall, F1 score and accuracy, and computational efficiency during testing." @default.
- W3197264024 created "2021-09-13" @default.
- W3197264024 creator A5011502544 @default.
- W3197264024 creator A5013135449 @default.
- W3197264024 creator A5025159531 @default.
- W3197264024 creator A5029808393 @default.
- W3197264024 creator A5042747240 @default.
- W3197264024 date "2021-01-01" @default.
- W3197264024 modified "2023-10-14" @default.
- W3197264024 title "Out-of-Distribution Detection for Deep Neural Networks With Isolation Forest and Local Outlier Factor" @default.
- W3197264024 cites W2007339694 @default.
- W3197264024 cites W2030224590 @default.
- W3197264024 cites W2117876524 @default.
- W3197264024 cites W2122646361 @default.
- W3197264024 cites W2296719434 @default.
- W3197264024 cites W2791467849 @default.
- W3197264024 cites W2798302089 @default.
- W3197264024 cites W2963668975 @default.
- W3197264024 cites W2981207549 @default.
- W3197264024 cites W2983029853 @default.
- W3197264024 cites W2984353870 @default.
- W3197264024 cites W2997212544 @default.
- W3197264024 cites W3007157104 @default.
- W3197264024 cites W3048679064 @default.
- W3197264024 cites W3095892876 @default.
- W3197264024 cites W3117098906 @default.
- W3197264024 cites W3118738952 @default.
- W3197264024 cites W3127561923 @default.
- W3197264024 cites W4254182148 @default.
- W3197264024 doi "https://doi.org/10.1109/access.2021.3108451" @default.
- W3197264024 hasPublicationYear "2021" @default.
- W3197264024 type Work @default.
- W3197264024 sameAs 3197264024 @default.
- W3197264024 citedByCount "12" @default.
- W3197264024 countsByYear W31972640242021 @default.
- W3197264024 countsByYear W31972640242022 @default.
- W3197264024 countsByYear W31972640242023 @default.
- W3197264024 crossrefType "journal-article" @default.
- W3197264024 hasAuthorship W3197264024A5011502544 @default.
- W3197264024 hasAuthorship W3197264024A5013135449 @default.
- W3197264024 hasAuthorship W3197264024A5025159531 @default.
- W3197264024 hasAuthorship W3197264024A5029808393 @default.
- W3197264024 hasAuthorship W3197264024A5042747240 @default.
- W3197264024 hasBestOaLocation W31972640241 @default.
- W3197264024 hasConcept C108583219 @default.
- W3197264024 hasConcept C119857082 @default.
- W3197264024 hasConcept C124101348 @default.
- W3197264024 hasConcept C153180895 @default.
- W3197264024 hasConcept C154945302 @default.
- W3197264024 hasConcept C169029474 @default.
- W3197264024 hasConcept C2775941552 @default.
- W3197264024 hasConcept C2776151529 @default.
- W3197264024 hasConcept C2984842247 @default.
- W3197264024 hasConcept C41008148 @default.
- W3197264024 hasConcept C50644808 @default.
- W3197264024 hasConcept C739882 @default.
- W3197264024 hasConcept C79337645 @default.
- W3197264024 hasConcept C86803240 @default.
- W3197264024 hasConcept C89423630 @default.
- W3197264024 hasConceptScore W3197264024C108583219 @default.
- W3197264024 hasConceptScore W3197264024C119857082 @default.
- W3197264024 hasConceptScore W3197264024C124101348 @default.
- W3197264024 hasConceptScore W3197264024C153180895 @default.
- W3197264024 hasConceptScore W3197264024C154945302 @default.
- W3197264024 hasConceptScore W3197264024C169029474 @default.
- W3197264024 hasConceptScore W3197264024C2775941552 @default.
- W3197264024 hasConceptScore W3197264024C2776151529 @default.
- W3197264024 hasConceptScore W3197264024C2984842247 @default.
- W3197264024 hasConceptScore W3197264024C41008148 @default.
- W3197264024 hasConceptScore W3197264024C50644808 @default.
- W3197264024 hasConceptScore W3197264024C739882 @default.
- W3197264024 hasConceptScore W3197264024C79337645 @default.
- W3197264024 hasConceptScore W3197264024C86803240 @default.
- W3197264024 hasConceptScore W3197264024C89423630 @default.
- W3197264024 hasFunder F4320321001 @default.
- W3197264024 hasLocation W31972640241 @default.
- W3197264024 hasLocation W31972640242 @default.
- W3197264024 hasOpenAccess W3197264024 @default.
- W3197264024 hasPrimaryLocation W31972640241 @default.
- W3197264024 hasRelatedWork W1991959600 @default.
- W3197264024 hasRelatedWork W2357795050 @default.
- W3197264024 hasRelatedWork W2369977179 @default.
- W3197264024 hasRelatedWork W2372407086 @default.
- W3197264024 hasRelatedWork W2885987569 @default.
- W3197264024 hasRelatedWork W2970686063 @default.
- W3197264024 hasRelatedWork W2971586703 @default.
- W3197264024 hasRelatedWork W3093275957 @default.
- W3197264024 hasRelatedWork W3116762327 @default.
- W3197264024 hasRelatedWork W3176177171 @default.
- W3197264024 hasVolume "9" @default.
- W3197264024 isParatext "false" @default.
- W3197264024 isRetracted "false" @default.
- W3197264024 magId "3197264024" @default.
- W3197264024 workType "article" @default.