FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3042418402> ?p ?o ?g. }

• W3042418402 abstract "Variational autoencoders (VAEs) are influential generative models with rich representation capabilities from the deep neural network architecture and Bayesian method. However, VAE models have a weakness that assign a higher likelihood to out-of-distribution (OOD) inputs than in-distribution (ID) inputs. To address this problem, a reliable uncertainty estimation is considered to be critical for in-depth understanding of OOD inputs. In this study, we propose an improved noise contrastive prior (INCP) to be able to integrate into the encoder of VAEs, called INCPVAE. INCP is scalable, trainable and compatible with VAEs, and it also adopts the merits from the INCP for uncertainty estimation. Experiments on various datasets demonstrate that compared to the standard VAEs, our model is superior in uncertainty estimation for the OOD data and is robust in anomaly detection tasks. The INCPVAE model obtains reliable uncertainty estimation for OOD inputs and solves the OOD problem in VAE models." @default.
• W3042418402 created "2020-07-23" @default.
• W3042418402 creator A5030409594 @default.
• W3042418402 creator A5058700999 @default.
• W3042418402 creator A5059986647 @default.
• W3042418402 creator A5072768654 @default.
• W3042418402 creator A5078854583 @default.
• W3042418402 date "2020-07-16" @default.
• W3042418402 modified "2023-09-27" @default.
• W3042418402 title "Detecting Out-of-distribution Samples via Variational Auto-encoder with Reliable Uncertainty Estimation" @default.
• W3042418402 cites W1909320841 @default.
• W3042418402 cites W1959608418 @default.
• W3042418402 cites W2123098109 @default.
• W3042418402 cites W2152790380 @default.
• W3042418402 cites W2267126114 @default.
• W3042418402 cites W2423557781 @default.
• W3042418402 cites W2531327146 @default.
• W3042418402 cites W2626967530 @default.
• W3042418402 cites W2808594940 @default.
• W3042418402 cites W2810676804 @default.
• W3042418402 cites W2884298516 @default.
• W3042418402 cites W2887286714 @default.
• W3042418402 cites W2889625178 @default.
• W3042418402 cites W2890591829 @default.
• W3042418402 cites W2896687685 @default.
• W3042418402 cites W2904693122 @default.
• W3042418402 cites W2904981516 @default.
• W3042418402 cites W2913300775 @default.
• W3042418402 cites W2948571844 @default.
• W3042418402 cites W2949982377 @default.
• W3042418402 cites W2962738009 @default.
• W3042418402 cites W2963082441 @default.
• W3042418402 cites W2963207607 @default.
• W3042418402 cites W2963238274 @default.
• W3042418402 cites W2963384319 @default.
• W3042418402 cites W2963693742 @default.
• W3042418402 cites W2964059111 @default.
• W3042418402 cites W2964466098 @default.
• W3042418402 cites W2970810885 @default.
• W3042418402 cites W2970946347 @default.
• W3042418402 cites W2980402966 @default.
• W3042418402 cites W2995140724 @default.
• W3042418402 cites W2995653243 @default.
• W3042418402 cites W2996156127 @default.
• W3042418402 cites W3005985924 @default.
• W3042418402 cites W3009328596 @default.
• W3042418402 cites W3099669512 @default.
• W3042418402 doi "https://doi.org/10.48550/arxiv.2007.08128" @default.
• W3042418402 hasPublicationYear "2020" @default.
• W3042418402 type Work @default.
• W3042418402 sameAs 3042418402 @default.
• W3042418402 citedByCount "3" @default.
• W3042418402 countsByYear W30424184022021 @default.
• W3042418402 crossrefType "posted-content" @default.
• W3042418402 hasAuthorship W3042418402A5030409594 @default.
• W3042418402 hasAuthorship W3042418402A5058700999 @default.
• W3042418402 hasAuthorship W3042418402A5059986647 @default.
• W3042418402 hasAuthorship W3042418402A5072768654 @default.
• W3042418402 hasAuthorship W3042418402A5078854583 @default.
• W3042418402 hasBestOaLocation W30424184021 @default.
• W3042418402 hasConcept C101738243 @default.
• W3042418402 hasConcept C111919701 @default.
• W3042418402 hasConcept C115961682 @default.
• W3042418402 hasConcept C118505674 @default.
• W3042418402 hasConcept C119857082 @default.
• W3042418402 hasConcept C124101348 @default.
• W3042418402 hasConcept C127413603 @default.
• W3042418402 hasConcept C153180895 @default.
• W3042418402 hasConcept C154945302 @default.
• W3042418402 hasConcept C17744445 @default.
• W3042418402 hasConcept C199539241 @default.
• W3042418402 hasConcept C201995342 @default.
• W3042418402 hasConcept C2776359362 @default.
• W3042418402 hasConcept C41008148 @default.
• W3042418402 hasConcept C48044578 @default.
• W3042418402 hasConcept C50644808 @default.
• W3042418402 hasConcept C739882 @default.
• W3042418402 hasConcept C77088390 @default.
• W3042418402 hasConcept C94625758 @default.
• W3042418402 hasConcept C96250715 @default.
• W3042418402 hasConcept C99498987 @default.
• W3042418402 hasConceptScore W3042418402C101738243 @default.
• W3042418402 hasConceptScore W3042418402C111919701 @default.
• W3042418402 hasConceptScore W3042418402C115961682 @default.
• W3042418402 hasConceptScore W3042418402C118505674 @default.
• W3042418402 hasConceptScore W3042418402C119857082 @default.
• W3042418402 hasConceptScore W3042418402C124101348 @default.
• W3042418402 hasConceptScore W3042418402C127413603 @default.
• W3042418402 hasConceptScore W3042418402C153180895 @default.
• W3042418402 hasConceptScore W3042418402C154945302 @default.
• W3042418402 hasConceptScore W3042418402C17744445 @default.
• W3042418402 hasConceptScore W3042418402C199539241 @default.
• W3042418402 hasConceptScore W3042418402C201995342 @default.
• W3042418402 hasConceptScore W3042418402C2776359362 @default.
• W3042418402 hasConceptScore W3042418402C41008148 @default.
• W3042418402 hasConceptScore W3042418402C48044578 @default.
• W3042418402 hasConceptScore W3042418402C50644808 @default.
• W3042418402 hasConceptScore W3042418402C739882 @default.
• W3042418402 hasConceptScore W3042418402C77088390 @default.
• W3042418402 hasConceptScore W3042418402C94625758 @default.

• next