Matches in SemOpenAlex for { <https://semopenalex.org/work/W3199372678> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3199372678 abstract "The identification of out-of-distribution data is vital to the deployment of classification networks. For example, a generic neural network that has been trained to differentiate between images of dogs and cats can only classify an input as either a dog or a cat. If a picture of a car or a kumquat were to be supplied to this classifier, the result would still be either a dog or a cat. In order to mitigate this, techniques such as the neural network watchdog have been developed. The compression of the image input into the latent layer of the autoencoder defines the region of in-distribution in the image space. This in-distribution set of input data has a corresponding boundary in the image space. The watchdog assesses whether inputs are in inside or outside this boundary. This paper demonstrates how to sharpen this boundary using generative network training data augmentation thereby bettering the discrimination and overall performance of the watchdog." @default.
- W3199372678 created "2021-09-27" @default.
- W3199372678 creator A5044513368 @default.
- W3199372678 creator A5064211368 @default.
- W3199372678 creator A5073896542 @default.
- W3199372678 date "2023-03-08" @default.
- W3199372678 modified "2023-10-14" @default.
- W3199372678 title "Generatively Augmented Neural Network Watchdog for Image Classification Networks" @default.
- W3199372678 cites W1511089533 @default.
- W3199372678 cites W1741361249 @default.
- W3199372678 cites W1849056616 @default.
- W3199372678 cites W1973207880 @default.
- W3199372678 cites W2041529686 @default.
- W3199372678 cites W2070211424 @default.
- W3199372678 cites W2099872269 @default.
- W3199372678 cites W2100324169 @default.
- W3199372678 cites W2104765221 @default.
- W3199372678 cites W2113833301 @default.
- W3199372678 cites W2119002676 @default.
- W3199372678 cites W2124048892 @default.
- W3199372678 cites W2129730156 @default.
- W3199372678 cites W2133665775 @default.
- W3199372678 cites W2138831092 @default.
- W3199372678 cites W2155368127 @default.
- W3199372678 cites W2159964742 @default.
- W3199372678 cites W2254039850 @default.
- W3199372678 cites W2737897717 @default.
- W3199372678 cites W2789481473 @default.
- W3199372678 cites W2791288760 @default.
- W3199372678 cites W2963541464 @default.
- W3199372678 cites W2979741026 @default.
- W3199372678 cites W3022746105 @default.
- W3199372678 cites W3127253295 @default.
- W3199372678 doi "https://doi.org/10.1109/ccwc57344.2023.10099329" @default.
- W3199372678 hasPublicationYear "2023" @default.
- W3199372678 type Work @default.
- W3199372678 sameAs 3199372678 @default.
- W3199372678 citedByCount "0" @default.
- W3199372678 crossrefType "proceedings-article" @default.
- W3199372678 hasAuthorship W3199372678A5044513368 @default.
- W3199372678 hasAuthorship W3199372678A5064211368 @default.
- W3199372678 hasAuthorship W3199372678A5073896542 @default.
- W3199372678 hasConcept C101738243 @default.
- W3199372678 hasConcept C105339364 @default.
- W3199372678 hasConcept C111919701 @default.
- W3199372678 hasConcept C115961682 @default.
- W3199372678 hasConcept C124101348 @default.
- W3199372678 hasConcept C134306372 @default.
- W3199372678 hasConcept C153180895 @default.
- W3199372678 hasConcept C154945302 @default.
- W3199372678 hasConcept C31972630 @default.
- W3199372678 hasConcept C33923547 @default.
- W3199372678 hasConcept C41008148 @default.
- W3199372678 hasConcept C50644808 @default.
- W3199372678 hasConcept C62354387 @default.
- W3199372678 hasConcept C75294576 @default.
- W3199372678 hasConcept C95623464 @default.
- W3199372678 hasConceptScore W3199372678C101738243 @default.
- W3199372678 hasConceptScore W3199372678C105339364 @default.
- W3199372678 hasConceptScore W3199372678C111919701 @default.
- W3199372678 hasConceptScore W3199372678C115961682 @default.
- W3199372678 hasConceptScore W3199372678C124101348 @default.
- W3199372678 hasConceptScore W3199372678C134306372 @default.
- W3199372678 hasConceptScore W3199372678C153180895 @default.
- W3199372678 hasConceptScore W3199372678C154945302 @default.
- W3199372678 hasConceptScore W3199372678C31972630 @default.
- W3199372678 hasConceptScore W3199372678C33923547 @default.
- W3199372678 hasConceptScore W3199372678C41008148 @default.
- W3199372678 hasConceptScore W3199372678C50644808 @default.
- W3199372678 hasConceptScore W3199372678C62354387 @default.
- W3199372678 hasConceptScore W3199372678C75294576 @default.
- W3199372678 hasConceptScore W3199372678C95623464 @default.
- W3199372678 hasLocation W31993726781 @default.
- W3199372678 hasOpenAccess W3199372678 @default.
- W3199372678 hasPrimaryLocation W31993726781 @default.
- W3199372678 hasRelatedWork W2163817528 @default.
- W3199372678 hasRelatedWork W2549006548 @default.
- W3199372678 hasRelatedWork W2592385986 @default.
- W3199372678 hasRelatedWork W2785535669 @default.
- W3199372678 hasRelatedWork W2807311372 @default.
- W3199372678 hasRelatedWork W2905846897 @default.
- W3199372678 hasRelatedWork W2972035100 @default.
- W3199372678 hasRelatedWork W3043252291 @default.
- W3199372678 hasRelatedWork W4214932115 @default.
- W3199372678 hasRelatedWork W4221015625 @default.
- W3199372678 isParatext "false" @default.
- W3199372678 isRetracted "false" @default.
- W3199372678 magId "3199372678" @default.
- W3199372678 workType "article" @default.