Matches in SemOpenAlex for { <https://semopenalex.org/work/W3048815401> ?p ?o ?g. }
- W3048815401 abstract "Although unsupervised generative modeling of an image dataset using a Variational AutoEncoder (VAE) has been used to detect anomalous images, or anomalous regions in images, recent works have shown that this method often identifies images or regions that do not concur with human perception, even questioning the usability of generative models for robust anomaly detection. Here, we argue that those issues can emerge from having a simplistic model of the anomaly distribution and we propose a new VAE-based model expressing a more complex anomaly model that is also closer to human perception. This Feature-Augmented VAE is trained by not only reconstructing the input image in pixel space, but also in several different feature spaces, which are computed by a convolutional neural network trained beforehand on a large image dataset. It achieves clear improvement over state-of-the-art methods on the MVTec anomaly detection and localization datasets." @default.
- W3048815401 created "2020-08-18" @default.
- W3048815401 creator A5059942051 @default.
- W3048815401 creator A5086578317 @default.
- W3048815401 date "2020-08-12" @default.
- W3048815401 modified "2023-09-27" @default.
- W3048815401 title "Anomaly localization by modeling perceptual features." @default.
- W3048815401 cites W1686810756 @default.
- W3048815401 cites W2099471712 @default.
- W3048815401 cites W2133665775 @default.
- W3048815401 cites W2335728318 @default.
- W3048815401 cites W2528578439 @default.
- W3048815401 cites W2577946330 @default.
- W3048815401 cites W2599354622 @default.
- W3048815401 cites W2784032999 @default.
- W3048815401 cites W2809705434 @default.
- W3048815401 cites W2884195445 @default.
- W3048815401 cites W2900627348 @default.
- W3048815401 cites W2911290044 @default.
- W3048815401 cites W2913300775 @default.
- W3048815401 cites W2914570111 @default.
- W3048815401 cites W2945655544 @default.
- W3048815401 cites W2948982773 @default.
- W3048815401 cites W2951004968 @default.
- W3048815401 cites W2962785568 @default.
- W3048815401 cites W2963541464 @default.
- W3048815401 cites W2963546708 @default.
- W3048815401 cites W2980402966 @default.
- W3048815401 cites W2982324952 @default.
- W3048815401 cites W2994613279 @default.
- W3048815401 cites W3034314048 @default.
- W3048815401 hasPublicationYear "2020" @default.
- W3048815401 type Work @default.
- W3048815401 sameAs 3048815401 @default.
- W3048815401 citedByCount "2" @default.
- W3048815401 countsByYear W30488154012021 @default.
- W3048815401 crossrefType "posted-content" @default.
- W3048815401 hasAuthorship W3048815401A5059942051 @default.
- W3048815401 hasAuthorship W3048815401A5086578317 @default.
- W3048815401 hasConcept C101738243 @default.
- W3048815401 hasConcept C115961682 @default.
- W3048815401 hasConcept C121332964 @default.
- W3048815401 hasConcept C12997251 @default.
- W3048815401 hasConcept C138885662 @default.
- W3048815401 hasConcept C153180895 @default.
- W3048815401 hasConcept C154945302 @default.
- W3048815401 hasConcept C15744967 @default.
- W3048815401 hasConcept C167966045 @default.
- W3048815401 hasConcept C169760540 @default.
- W3048815401 hasConcept C26760741 @default.
- W3048815401 hasConcept C26873012 @default.
- W3048815401 hasConcept C2776401178 @default.
- W3048815401 hasConcept C39890363 @default.
- W3048815401 hasConcept C41008148 @default.
- W3048815401 hasConcept C41895202 @default.
- W3048815401 hasConcept C50644808 @default.
- W3048815401 hasConcept C739882 @default.
- W3048815401 hasConcept C81363708 @default.
- W3048815401 hasConcept C83665646 @default.
- W3048815401 hasConceptScore W3048815401C101738243 @default.
- W3048815401 hasConceptScore W3048815401C115961682 @default.
- W3048815401 hasConceptScore W3048815401C121332964 @default.
- W3048815401 hasConceptScore W3048815401C12997251 @default.
- W3048815401 hasConceptScore W3048815401C138885662 @default.
- W3048815401 hasConceptScore W3048815401C153180895 @default.
- W3048815401 hasConceptScore W3048815401C154945302 @default.
- W3048815401 hasConceptScore W3048815401C15744967 @default.
- W3048815401 hasConceptScore W3048815401C167966045 @default.
- W3048815401 hasConceptScore W3048815401C169760540 @default.
- W3048815401 hasConceptScore W3048815401C26760741 @default.
- W3048815401 hasConceptScore W3048815401C26873012 @default.
- W3048815401 hasConceptScore W3048815401C2776401178 @default.
- W3048815401 hasConceptScore W3048815401C39890363 @default.
- W3048815401 hasConceptScore W3048815401C41008148 @default.
- W3048815401 hasConceptScore W3048815401C41895202 @default.
- W3048815401 hasConceptScore W3048815401C50644808 @default.
- W3048815401 hasConceptScore W3048815401C739882 @default.
- W3048815401 hasConceptScore W3048815401C81363708 @default.
- W3048815401 hasConceptScore W3048815401C83665646 @default.
- W3048815401 hasLocation W30488154011 @default.
- W3048815401 hasOpenAccess W3048815401 @default.
- W3048815401 hasPrimaryLocation W30488154011 @default.
- W3048815401 hasRelatedWork W2613600988 @default.
- W3048815401 hasRelatedWork W2904013130 @default.
- W3048815401 hasRelatedWork W2914570111 @default.
- W3048815401 hasRelatedWork W2964989774 @default.
- W3048815401 hasRelatedWork W2997229301 @default.
- W3048815401 hasRelatedWork W3006797839 @default.
- W3048815401 hasRelatedWork W3012693338 @default.
- W3048815401 hasRelatedWork W3082546531 @default.
- W3048815401 hasRelatedWork W3091561623 @default.
- W3048815401 hasRelatedWork W3099658315 @default.
- W3048815401 hasRelatedWork W3114010851 @default.
- W3048815401 hasRelatedWork W3114991260 @default.
- W3048815401 hasRelatedWork W3138070353 @default.
- W3048815401 hasRelatedWork W3157994340 @default.
- W3048815401 hasRelatedWork W3158969151 @default.
- W3048815401 hasRelatedWork W3160467203 @default.
- W3048815401 hasRelatedWork W3173538657 @default.
- W3048815401 hasRelatedWork W3175238080 @default.