Matches in SemOpenAlex for { <https://semopenalex.org/work/W4299830485> ?p ?o ?g. }
Showing items 1 to 62 of
62
with 100 items per page.
- W4299830485 abstract "Video games are a compelling source of annotated data as they can readily provide fine-grained groundtruth for diverse tasks. However, it is not clear whether the synthetically generated data has enough resemblance to the real-world images to improve the performance of computer vision models in practice. We present experiments assessing the effectiveness on real-world data of systems trained on synthetic RGB images that are extracted from a video game. We collected over 60000 synthetic samples from a modern video game with similar conditions to the real-world CamVid and Cityscapes datasets. We provide several experiments to demonstrate that the synthetically generated RGB images can be used to improve the performance of deep neural networks on both image segmentation and depth estimation. These results show that a convolutional network trained on synthetic data achieves a similar test error to a network that is trained on real-world data for dense image classification. Furthermore, the synthetically generated RGB images can provide similar or better results compared to the real-world datasets if a simple domain adaptation technique is applied. Our results suggest that collaboration with game developers for an accessible interface to gather data is potentially a fruitful direction for future work in computer vision." @default.
- W4299830485 created "2022-10-03" @default.
- W4299830485 creator A5007777373 @default.
- W4299830485 creator A5010139488 @default.
- W4299830485 creator A5078801359 @default.
- W4299830485 date "2016-08-04" @default.
- W4299830485 modified "2023-10-18" @default.
- W4299830485 title "Play and Learn: Using Video Games to Train Computer Vision Models" @default.
- W4299830485 doi "https://doi.org/10.48550/arxiv.1608.01745" @default.
- W4299830485 hasPublicationYear "2016" @default.
- W4299830485 type Work @default.
- W4299830485 citedByCount "0" @default.
- W4299830485 crossrefType "posted-content" @default.
- W4299830485 hasAuthorship W4299830485A5007777373 @default.
- W4299830485 hasAuthorship W4299830485A5010139488 @default.
- W4299830485 hasAuthorship W4299830485A5078801359 @default.
- W4299830485 hasBestOaLocation W42998304851 @default.
- W4299830485 hasConcept C119857082 @default.
- W4299830485 hasConcept C120665830 @default.
- W4299830485 hasConcept C121332964 @default.
- W4299830485 hasConcept C139807058 @default.
- W4299830485 hasConcept C154945302 @default.
- W4299830485 hasConcept C160920958 @default.
- W4299830485 hasConcept C3018412434 @default.
- W4299830485 hasConcept C31972630 @default.
- W4299830485 hasConcept C41008148 @default.
- W4299830485 hasConcept C49774154 @default.
- W4299830485 hasConcept C50644808 @default.
- W4299830485 hasConcept C81363708 @default.
- W4299830485 hasConcept C82990744 @default.
- W4299830485 hasConcept C89600930 @default.
- W4299830485 hasConceptScore W4299830485C119857082 @default.
- W4299830485 hasConceptScore W4299830485C120665830 @default.
- W4299830485 hasConceptScore W4299830485C121332964 @default.
- W4299830485 hasConceptScore W4299830485C139807058 @default.
- W4299830485 hasConceptScore W4299830485C154945302 @default.
- W4299830485 hasConceptScore W4299830485C160920958 @default.
- W4299830485 hasConceptScore W4299830485C3018412434 @default.
- W4299830485 hasConceptScore W4299830485C31972630 @default.
- W4299830485 hasConceptScore W4299830485C41008148 @default.
- W4299830485 hasConceptScore W4299830485C49774154 @default.
- W4299830485 hasConceptScore W4299830485C50644808 @default.
- W4299830485 hasConceptScore W4299830485C81363708 @default.
- W4299830485 hasConceptScore W4299830485C82990744 @default.
- W4299830485 hasConceptScore W4299830485C89600930 @default.
- W4299830485 hasLocation W42998304851 @default.
- W4299830485 hasLocation W42998304852 @default.
- W4299830485 hasOpenAccess W4299830485 @default.
- W4299830485 hasPrimaryLocation W42998304851 @default.
- W4299830485 hasRelatedWork W2318112981 @default.
- W4299830485 hasRelatedWork W2811106690 @default.
- W4299830485 hasRelatedWork W2936819511 @default.
- W4299830485 hasRelatedWork W2947043951 @default.
- W4299830485 hasRelatedWork W4239306820 @default.
- W4299830485 hasRelatedWork W4293226380 @default.
- W4299830485 hasRelatedWork W4312417841 @default.
- W4299830485 hasRelatedWork W4313906399 @default.
- W4299830485 hasRelatedWork W4321444604 @default.
- W4299830485 hasRelatedWork W4321487865 @default.
- W4299830485 isParatext "false" @default.
- W4299830485 isRetracted "false" @default.
- W4299830485 workType "article" @default.