Matches in SemOpenAlex for { <https://semopenalex.org/work/W2767194911> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2767194911 abstract "Dropout Variational Inference, or Dropout Sampling, has been recently proposed as an approximation technique for Bayesian Deep Learning and evaluated for image classification and regression tasks. This paper investigates the utility of Dropout Sampling for object detection for the first time. We demonstrate how label uncertainty can be extracted from a state-of-the-art object detection system via Dropout Sampling. We evaluate this approach on a large synthetic dataset of 30,000 images, and a real-world dataset captured by a mobile robot in a versatile campus environment. We show that this uncertainty can be utilized to increase object detection performance under the open-set conditions that are typically encountered in robotic vision. A Dropout Sampling network is shown to achieve a 12.3% increase in recall (for the same precision score as a standard network) and a 15.1% increase in precision (for the same recall score as the standard network)." @default.
- W2767194911 created "2017-11-10" @default.
- W2767194911 creator A5004010259 @default.
- W2767194911 creator A5034957065 @default.
- W2767194911 creator A5059620284 @default.
- W2767194911 creator A5091323624 @default.
- W2767194911 date "2017-10-18" @default.
- W2767194911 modified "2023-09-27" @default.
- W2767194911 title "Dropout Sampling for Robust Object Detection in Open-Set Conditions" @default.
- W2767194911 cites W1567512734 @default.
- W2767194911 cites W1861492603 @default.
- W2767194911 cites W1909320841 @default.
- W2767194911 cites W1959608418 @default.
- W2767194911 cites W2031342017 @default.
- W2767194911 cites W2102605133 @default.
- W2767194911 cites W2103328396 @default.
- W2767194911 cites W2111051539 @default.
- W2767194911 cites W2119880843 @default.
- W2767194911 cites W2150807068 @default.
- W2767194911 cites W2166851633 @default.
- W2767194911 cites W2402652555 @default.
- W2767194911 cites W2570343428 @default.
- W2767194911 cites W2613718673 @default.
- W2767194911 cites W2743154296 @default.
- W2767194911 cites W2780351918 @default.
- W2767194911 cites W2950517871 @default.
- W2767194911 cites W2951493172 @default.
- W2767194911 cites W2962835968 @default.
- W2767194911 cites W2963024893 @default.
- W2767194911 cites W2963149653 @default.
- W2767194911 cites W2964059111 @default.
- W2767194911 cites W572355794 @default.
- W2767194911 hasPublicationYear "2017" @default.
- W2767194911 type Work @default.
- W2767194911 sameAs 2767194911 @default.
- W2767194911 citedByCount "1" @default.
- W2767194911 countsByYear W27671949112020 @default.
- W2767194911 crossrefType "posted-content" @default.
- W2767194911 hasAuthorship W2767194911A5004010259 @default.
- W2767194911 hasAuthorship W2767194911A5034957065 @default.
- W2767194911 hasAuthorship W2767194911A5059620284 @default.
- W2767194911 hasAuthorship W2767194911A5091323624 @default.
- W2767194911 hasConcept C106131492 @default.
- W2767194911 hasConcept C119857082 @default.
- W2767194911 hasConcept C140779682 @default.
- W2767194911 hasConcept C153180895 @default.
- W2767194911 hasConcept C154945302 @default.
- W2767194911 hasConcept C177264268 @default.
- W2767194911 hasConcept C199360897 @default.
- W2767194911 hasConcept C2776145597 @default.
- W2767194911 hasConcept C2776151529 @default.
- W2767194911 hasConcept C2776214188 @default.
- W2767194911 hasConcept C2781238097 @default.
- W2767194911 hasConcept C31972630 @default.
- W2767194911 hasConcept C33724603 @default.
- W2767194911 hasConcept C41008148 @default.
- W2767194911 hasConcept C81669768 @default.
- W2767194911 hasConceptScore W2767194911C106131492 @default.
- W2767194911 hasConceptScore W2767194911C119857082 @default.
- W2767194911 hasConceptScore W2767194911C140779682 @default.
- W2767194911 hasConceptScore W2767194911C153180895 @default.
- W2767194911 hasConceptScore W2767194911C154945302 @default.
- W2767194911 hasConceptScore W2767194911C177264268 @default.
- W2767194911 hasConceptScore W2767194911C199360897 @default.
- W2767194911 hasConceptScore W2767194911C2776145597 @default.
- W2767194911 hasConceptScore W2767194911C2776151529 @default.
- W2767194911 hasConceptScore W2767194911C2776214188 @default.
- W2767194911 hasConceptScore W2767194911C2781238097 @default.
- W2767194911 hasConceptScore W2767194911C31972630 @default.
- W2767194911 hasConceptScore W2767194911C33724603 @default.
- W2767194911 hasConceptScore W2767194911C41008148 @default.
- W2767194911 hasConceptScore W2767194911C81669768 @default.
- W2767194911 hasLocation W27671949111 @default.
- W2767194911 hasOpenAccess W2767194911 @default.
- W2767194911 hasPrimaryLocation W27671949111 @default.
- W2767194911 hasRelatedWork W1995139233 @default.
- W2767194911 hasRelatedWork W2090563602 @default.
- W2767194911 hasRelatedWork W2101937459 @default.
- W2767194911 hasRelatedWork W2114361718 @default.
- W2767194911 hasRelatedWork W2774446296 @default.
- W2767194911 hasRelatedWork W2888842227 @default.
- W2767194911 hasRelatedWork W2899565378 @default.
- W2767194911 hasRelatedWork W2911066482 @default.
- W2767194911 hasRelatedWork W2979631643 @default.
- W2767194911 hasRelatedWork W2997591247 @default.
- W2767194911 hasRelatedWork W3007201890 @default.
- W2767194911 hasRelatedWork W3041214840 @default.
- W2767194911 hasRelatedWork W3135252693 @default.
- W2767194911 hasRelatedWork W3163754314 @default.
- W2767194911 hasRelatedWork W3169662560 @default.
- W2767194911 hasRelatedWork W3175255259 @default.
- W2767194911 hasRelatedWork W3175492751 @default.
- W2767194911 hasRelatedWork W3179601479 @default.
- W2767194911 hasRelatedWork W2138866680 @default.
- W2767194911 hasRelatedWork W3129266002 @default.
- W2767194911 isParatext "false" @default.
- W2767194911 isRetracted "false" @default.
- W2767194911 magId "2767194911" @default.
- W2767194911 workType "article" @default.