FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312948137> ?p ?o ?g. }

• W4312948137 abstract "Effectively utilizing the vast amounts of ego-centric navigation data that is freely available on the internet can advance generalized intelligent systems, i.e., to robustly scale across perspectives, platforms, environmental conditions, scenarios, and geographical locations. However, it is difficult to directly leverage such large amounts of unlabeled and highly diverse datafor complex 3D reasoning and planning tasks. Consequently, researchers have primarily focused on its use for various auxiliary pixel- and image-level computer vision tasks that do not consider an ultimate navigational objective. In this work, we introduce SelfD, a framework for learning scalable driving by utilizing large amounts of online monocular images. Our key idea is to leverage iterative semi-supervised training when learning imitative agents from unlabeled data. To handle unconstrained viewpoints, scenes, and camera parameters, we train an image-based model that directly learns to plan in the Bird's Eye View (BEV) space. Next, we use unla-beled data to augment the decision-making knowledge and robustness of an initially trained model via self-training. In particular, we propose a pseudo-labeling step which enables making full use of highly diverse demonstration data through “hypothetical” planning-based data augmentation. We employ a large dataset of publicly available YouTube videos to train SelfD and comprehensively analyze its generalization benefits across challenging navigation scenarios. Without requiring any additional data collection or annotation efforts, SelfD demonstrates consistent improvements (by up to 24%) in driving performance evaluation on nuScenes, Argoverse, Waymo, and CARLA." @default.
• W4312948137 created "2023-01-05" @default.
• W4312948137 creator A5025893246 @default.
• W4312948137 creator A5053034350 @default.
• W4312948137 creator A5053113675 @default.
• W4312948137 date "2022-06-01" @default.
• W4312948137 modified "2023-09-30" @default.
• W4312948137 title "SelfD: Self-Learning Large-Scale Driving Policies From the Web" @default.
• W4312948137 cites W1584687743 @default.
• W4312948137 cites W1979841516 @default.
• W4312948137 cites W1999874108 @default.
• W4312948137 cites W2119112357 @default.
• W4312948137 cites W2124219775 @default.
• W4312948137 cites W2150066425 @default.
• W4312948137 cites W2321533354 @default.
• W4312948137 cites W2326925005 @default.
• W4312948137 cites W2340897893 @default.
• W4312948137 cites W2427448504 @default.
• W4312948137 cites W2559767995 @default.
• W4312948137 cites W2569836025 @default.
• W4312948137 cites W2593841437 @default.
• W4312948137 cites W2598706937 @default.
• W4312948137 cites W2837605352 @default.
• W4312948137 cites W2902855213 @default.
• W4312948137 cites W2942368658 @default.
• W4312948137 cites W2955189650 @default.
• W4312948137 cites W2962787969 @default.
• W4312948137 cites W2962894046 @default.
• W4312948137 cites W2963409832 @default.
• W4312948137 cites W2964460729 @default.
• W4312948137 cites W2967043539 @default.
• W4312948137 cites W2967464230 @default.
• W4312948137 cites W2979863294 @default.
• W4312948137 cites W2981732213 @default.
• W4312948137 cites W2982102242 @default.
• W4312948137 cites W2982496462 @default.
• W4312948137 cites W2985775862 @default.
• W4312948137 cites W2990873191 @default.
• W4312948137 cites W3003639745 @default.
• W4312948137 cites W3009593063 @default.
• W4312948137 cites W3034239557 @default.
• W4312948137 cites W3034308492 @default.
• W4312948137 cites W3034445502 @default.
• W4312948137 cites W3034552332 @default.
• W4312948137 cites W3034652687 @default.
• W4312948137 cites W3035056458 @default.
• W4312948137 cites W3035172746 @default.
• W4312948137 cites W3035524453 @default.
• W4312948137 cites W3090153548 @default.
• W4312948137 cites W3101780148 @default.
• W4312948137 cites W3102597561 @default.
• W4312948137 cites W3131287736 @default.
• W4312948137 cites W3172863135 @default.
• W4312948137 cites W3174177541 @default.
• W4312948137 cites W3175269419 @default.
• W4312948137 cites W3175682855 @default.
• W4312948137 cites W3180680946 @default.
• W4312948137 cites W3204659849 @default.
• W4312948137 cites W4214562507 @default.
• W4312948137 cites W4214759451 @default.
• W4312948137 doi "https://doi.org/10.1109/cvpr52688.2022.01680" @default.
• W4312948137 hasPublicationYear "2022" @default.
• W4312948137 type Work @default.
• W4312948137 citedByCount "2" @default.
• W4312948137 countsByYear W43129481372022 @default.
• W4312948137 countsByYear W43129481372023 @default.
• W4312948137 crossrefType "proceedings-article" @default.
• W4312948137 hasAuthorship W4312948137A5025893246 @default.
• W4312948137 hasAuthorship W4312948137A5053034350 @default.
• W4312948137 hasAuthorship W4312948137A5053113675 @default.
• W4312948137 hasBestOaLocation W43129481372 @default.
• W4312948137 hasConcept C104317684 @default.
• W4312948137 hasConcept C110875604 @default.
• W4312948137 hasConcept C119857082 @default.
• W4312948137 hasConcept C136764020 @default.
• W4312948137 hasConcept C142362112 @default.
• W4312948137 hasConcept C153083717 @default.
• W4312948137 hasConcept C153349607 @default.
• W4312948137 hasConcept C154945302 @default.
• W4312948137 hasConcept C185592680 @default.
• W4312948137 hasConcept C2776035091 @default.
• W4312948137 hasConcept C41008148 @default.
• W4312948137 hasConcept C48044578 @default.
• W4312948137 hasConcept C55493867 @default.
• W4312948137 hasConcept C63479239 @default.
• W4312948137 hasConcept C77088390 @default.
• W4312948137 hasConceptScore W4312948137C104317684 @default.
• W4312948137 hasConceptScore W4312948137C110875604 @default.
• W4312948137 hasConceptScore W4312948137C119857082 @default.
• W4312948137 hasConceptScore W4312948137C136764020 @default.
• W4312948137 hasConceptScore W4312948137C142362112 @default.
• W4312948137 hasConceptScore W4312948137C153083717 @default.
• W4312948137 hasConceptScore W4312948137C153349607 @default.
• W4312948137 hasConceptScore W4312948137C154945302 @default.
• W4312948137 hasConceptScore W4312948137C185592680 @default.
• W4312948137 hasConceptScore W4312948137C2776035091 @default.
• W4312948137 hasConceptScore W4312948137C41008148 @default.
• W4312948137 hasConceptScore W4312948137C48044578 @default.
• W4312948137 hasConceptScore W4312948137C55493867 @default.
• W4312948137 hasConceptScore W4312948137C63479239 @default.

• next