computational-label-and-data-efficiency-in-deep-learning-for-sparse-3d-data.pdf

Deep learning is widely applied to sparse 3D data to perform challenging tasks, e.g., 3D object detection and semantic segmentation. However, the high performance of deep learning comes with high costs, including computational costs and the effort to capture and label data. This work investigates an...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής
Γλώσσα:English
Έκδοση: KIT Scientific Publishing 2024
Διαθέσιμο Online:https://doi.org/10.5445/KSP/1000168541
id oapen-20.500.12657-90368
record_format dspace
spelling oapen-20.500.12657-903682024-05-22T02:23:02Z Computational, Label, and Data Efficiency in Deep Learning for Sparse 3D Data Li, Lanxiao Efficiency; 3D Data; Artificial Intelligence; Effizienz; 3D-Daten; Künstliche Intelligenz; Deep Learning thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TH Energy technology and engineering::THR Electrical engineering Deep learning is widely applied to sparse 3D data to perform challenging tasks, e.g., 3D object detection and semantic segmentation. However, the high performance of deep learning comes with high costs, including computational costs and the effort to capture and label data. This work investigates and improves the efficiency of deep learning for sparse 3D data to overcome the obstacles to the further development of this technology. 2024-05-21T07:51:03Z 2024-05-21T07:51:03Z 2024 book https://library.oapen.org/handle/20.500.12657/90368 eng Forschungsberichte aus der Industriellen Informationstechnik application/pdf Attribution-ShareAlike 4.0 International computational-label-and-data-efficiency-in-deep-learning-for-sparse-3d-data.pdf https://doi.org/10.5445/KSP/1000168541 KIT Scientific Publishing 10.5445/KSP/1000168541 10.5445/KSP/1000168541 44e29711-8d53-496b-85cc-3d10c9469be9 33 256 open access
institution OAPEN
collection DSpace
language English
description Deep learning is widely applied to sparse 3D data to perform challenging tasks, e.g., 3D object detection and semantic segmentation. However, the high performance of deep learning comes with high costs, including computational costs and the effort to capture and label data. This work investigates and improves the efficiency of deep learning for sparse 3D data to overcome the obstacles to the further development of this technology.
title computational-label-and-data-efficiency-in-deep-learning-for-sparse-3d-data.pdf
spellingShingle computational-label-and-data-efficiency-in-deep-learning-for-sparse-3d-data.pdf
title_short computational-label-and-data-efficiency-in-deep-learning-for-sparse-3d-data.pdf
title_full computational-label-and-data-efficiency-in-deep-learning-for-sparse-3d-data.pdf
title_fullStr computational-label-and-data-efficiency-in-deep-learning-for-sparse-3d-data.pdf
title_full_unstemmed computational-label-and-data-efficiency-in-deep-learning-for-sparse-3d-data.pdf
title_sort computational-label-and-data-efficiency-in-deep-learning-for-sparse-3d-data.pdf
publisher KIT Scientific Publishing
publishDate 2024
url https://doi.org/10.5445/KSP/1000168541
_version_ 1799945237302345728