Matches in SemOpenAlex for { <https://semopenalex.org/work/W2902277560> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2902277560 abstract "Deep learning models are known to be overconfident in their predictions on out of distribution inputs. There have been several pieces of work to address this issue, including a number of approaches for building Bayesian neural networks, as well as closely related work on detection of out of distribution samples. Recently, there has been work on building classifiers that are robust to out of distribution samples by adding a regularization term that maximizes the entropy of the classifier output on out of distribution data. To approximate out of distribution samples (which are not known apriori), a GAN was used for generation of samples at the edges of the training distribution. In this paper, we introduce an alternative GAN based approach for building a robust classifier, where the idea is to use the GAN to explicitly generate out of distribution samples that the classifier is confident on (low entropy), and have the classifier maximize the entropy for these samples. We showcase the effectiveness of our approach relative to state-of-the-art on hand-written characters as well as on a variety of natural image datasets." @default.
- W2902277560 created "2018-12-11" @default.
- W2902277560 creator A5049627979 @default.
- W2902277560 creator A5066300566 @default.
- W2902277560 date "2018-12-01" @default.
- W2902277560 modified "2023-09-27" @default.
- W2902277560 title "Building robust classifiers through generation of confident out of distribution examples" @default.
- W2902277560 cites W2173520492 @default.
- W2902277560 cites W2531327146 @default.
- W2902277560 cites W2590796488 @default.
- W2902277560 cites W2605055943 @default.
- W2902277560 cites W2750384547 @default.
- W2902277560 cites W2867167548 @default.
- W2902277560 cites W2963384319 @default.
- W2902277560 cites W2963693742 @default.
- W2902277560 cites W967544008 @default.
- W2902277560 hasPublicationYear "2018" @default.
- W2902277560 type Work @default.
- W2902277560 sameAs 2902277560 @default.
- W2902277560 citedByCount "10" @default.
- W2902277560 countsByYear W29022775602019 @default.
- W2902277560 countsByYear W29022775602020 @default.
- W2902277560 countsByYear W29022775602021 @default.
- W2902277560 countsByYear W29022775602022 @default.
- W2902277560 crossrefType "posted-content" @default.
- W2902277560 hasAuthorship W2902277560A5049627979 @default.
- W2902277560 hasAuthorship W2902277560A5066300566 @default.
- W2902277560 hasConcept C106301342 @default.
- W2902277560 hasConcept C107673813 @default.
- W2902277560 hasConcept C119857082 @default.
- W2902277560 hasConcept C121332964 @default.
- W2902277560 hasConcept C153180895 @default.
- W2902277560 hasConcept C154945302 @default.
- W2902277560 hasConcept C41008148 @default.
- W2902277560 hasConcept C50644808 @default.
- W2902277560 hasConcept C62520636 @default.
- W2902277560 hasConcept C95623464 @default.
- W2902277560 hasConceptScore W2902277560C106301342 @default.
- W2902277560 hasConceptScore W2902277560C107673813 @default.
- W2902277560 hasConceptScore W2902277560C119857082 @default.
- W2902277560 hasConceptScore W2902277560C121332964 @default.
- W2902277560 hasConceptScore W2902277560C153180895 @default.
- W2902277560 hasConceptScore W2902277560C154945302 @default.
- W2902277560 hasConceptScore W2902277560C41008148 @default.
- W2902277560 hasConceptScore W2902277560C50644808 @default.
- W2902277560 hasConceptScore W2902277560C62520636 @default.
- W2902277560 hasConceptScore W2902277560C95623464 @default.
- W2902277560 hasLocation W29022775601 @default.
- W2902277560 hasOpenAccess W2902277560 @default.
- W2902277560 hasPrimaryLocation W29022775601 @default.
- W2902277560 hasRelatedWork W103332046 @default.
- W2902277560 hasRelatedWork W1868310337 @default.
- W2902277560 hasRelatedWork W1970077680 @default.
- W2902277560 hasRelatedWork W2099471712 @default.
- W2902277560 hasRelatedWork W2335728318 @default.
- W2902277560 hasRelatedWork W2531327146 @default.
- W2902277560 hasRelatedWork W2867167548 @default.
- W2902277560 hasRelatedWork W2904981516 @default.
- W2902277560 hasRelatedWork W2949123531 @default.
- W2902277560 hasRelatedWork W2951544399 @default.
- W2902277560 hasRelatedWork W2963215553 @default.
- W2902277560 hasRelatedWork W2963384319 @default.
- W2902277560 hasRelatedWork W2963546708 @default.
- W2902277560 hasRelatedWork W2963693742 @default.
- W2902277560 hasRelatedWork W2970946347 @default.
- W2902277560 hasRelatedWork W2979332623 @default.
- W2902277560 hasRelatedWork W3021965991 @default.
- W2902277560 hasRelatedWork W3118608800 @default.
- W2902277560 hasRelatedWork W2181382496 @default.
- W2902277560 hasRelatedWork W2343000773 @default.
- W2902277560 isParatext "false" @default.
- W2902277560 isRetracted "false" @default.
- W2902277560 magId "2902277560" @default.
- W2902277560 workType "article" @default.