Matches in SemOpenAlex for { <https://semopenalex.org/work/W3196294098> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W3196294098 abstract "Training data is an essential ingredient within supervised learning, but time consuming, expensive and for some applications impossible to acquire. A possible solution is to use synthetic training data. However, the domain shift of synthetic data makes it challenging to obtain good results when used as training data for deep learning models. It is therefore of interest to refine synthetic data, e.g. using image-to-image translation, to improve results. The aim of this work is to compare different methods to do image-to-image translation of synthetic training data of thermal IR-images using generative adversarial networks (GANs). Translation is done both using synthetic thermal IR-images alone, as well as including pixelwise depth and/or semantic information. To evaluate, we propose a new measure based on the Frechet Inception Distance, adapted to work for thermal IR-images. We show that by adapting a GAN model to also include corresponding pixelwise depth data to each synthetic IR-image, the performance is improved compared to using only IR-images." @default.
- W3196294098 created "2021-09-13" @default.
- W3196294098 creator A5070586221 @default.
- W3196294098 creator A5091034308 @default.
- W3196294098 date "2021-09-12" @default.
- W3196294098 modified "2023-10-14" @default.
- W3196294098 title "Image-to-image translation for improvement of synthetic thermal infrared training data using generative adversarial networks" @default.
- W3196294098 cites W1686810756 @default.
- W3196294098 cites W1901129140 @default.
- W3196294098 cites W2173520492 @default.
- W3196294098 cites W2593768305 @default.
- W3196294098 cites W2605102758 @default.
- W3196294098 cites W2908033367 @default.
- W3196294098 cites W2950863313 @default.
- W3196294098 cites W2962793481 @default.
- W3196294098 cites W2963163009 @default.
- W3196294098 cites W2963373786 @default.
- W3196294098 doi "https://doi.org/10.1117/12.2599214" @default.
- W3196294098 hasPublicationYear "2021" @default.
- W3196294098 type Work @default.
- W3196294098 sameAs 3196294098 @default.
- W3196294098 citedByCount "1" @default.
- W3196294098 countsByYear W31962940982023 @default.
- W3196294098 crossrefType "proceedings-article" @default.
- W3196294098 hasAuthorship W3196294098A5070586221 @default.
- W3196294098 hasAuthorship W3196294098A5091034308 @default.
- W3196294098 hasBestOaLocation W31962940982 @default.
- W3196294098 hasConcept C104317684 @default.
- W3196294098 hasConcept C105580179 @default.
- W3196294098 hasConcept C108583219 @default.
- W3196294098 hasConcept C115961682 @default.
- W3196294098 hasConcept C119857082 @default.
- W3196294098 hasConcept C149364088 @default.
- W3196294098 hasConcept C153180895 @default.
- W3196294098 hasConcept C154945302 @default.
- W3196294098 hasConcept C160920958 @default.
- W3196294098 hasConcept C185592680 @default.
- W3196294098 hasConcept C2779757391 @default.
- W3196294098 hasConcept C2988773926 @default.
- W3196294098 hasConcept C31972630 @default.
- W3196294098 hasConcept C41008148 @default.
- W3196294098 hasConcept C51632099 @default.
- W3196294098 hasConcept C55493867 @default.
- W3196294098 hasConceptScore W3196294098C104317684 @default.
- W3196294098 hasConceptScore W3196294098C105580179 @default.
- W3196294098 hasConceptScore W3196294098C108583219 @default.
- W3196294098 hasConceptScore W3196294098C115961682 @default.
- W3196294098 hasConceptScore W3196294098C119857082 @default.
- W3196294098 hasConceptScore W3196294098C149364088 @default.
- W3196294098 hasConceptScore W3196294098C153180895 @default.
- W3196294098 hasConceptScore W3196294098C154945302 @default.
- W3196294098 hasConceptScore W3196294098C160920958 @default.
- W3196294098 hasConceptScore W3196294098C185592680 @default.
- W3196294098 hasConceptScore W3196294098C2779757391 @default.
- W3196294098 hasConceptScore W3196294098C2988773926 @default.
- W3196294098 hasConceptScore W3196294098C31972630 @default.
- W3196294098 hasConceptScore W3196294098C41008148 @default.
- W3196294098 hasConceptScore W3196294098C51632099 @default.
- W3196294098 hasConceptScore W3196294098C55493867 @default.
- W3196294098 hasLocation W31962940981 @default.
- W3196294098 hasLocation W31962940982 @default.
- W3196294098 hasOpenAccess W3196294098 @default.
- W3196294098 hasPrimaryLocation W31962940981 @default.
- W3196294098 hasRelatedWork W10927761 @default.
- W3196294098 hasRelatedWork W10944326 @default.
- W3196294098 hasRelatedWork W11117469 @default.
- W3196294098 hasRelatedWork W11664329 @default.
- W3196294098 hasRelatedWork W354571 @default.
- W3196294098 hasRelatedWork W6368054 @default.
- W3196294098 hasRelatedWork W6468916 @default.
- W3196294098 hasRelatedWork W674670 @default.
- W3196294098 hasRelatedWork W6770330 @default.
- W3196294098 hasRelatedWork W9190101 @default.
- W3196294098 isParatext "false" @default.
- W3196294098 isRetracted "false" @default.
- W3196294098 magId "3196294098" @default.
- W3196294098 workType "article" @default.