Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323543671> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4323543671 endingPage "44" @default.
- W4323543671 startingPage "30" @default.
- W4323543671 abstract "One of the major focuses in the remote sensing community is the rapid processing of deep neural networks (DNNs) on very high resolution (VHR) aerial images. Few studies have investigated the acceleration of training and prediction by optimizing the architecture of the DNN system rather than designing a lightweight DNN. Parallel processing using multiple graphics processing units (GPUs) increases VHR image processing performance. It drives extremely large and frequent data transfers (input/output(I/O)) from random access memory (RAM) to GPU memory. As a result, the system bus congestion causes the system to hang, resulting in long latency in training/predicting. In this paper, we evaluate the causes of long latency and propose a space-to-speed (S2S) DNN system to overcome the aforementioned challenges. A three-level memory system aiming to reduce data transfer during system operation is presented. Distribution optimization with parallel processing was used to accelerate the training. Training optimizations on VHR images (such as hot-zone searching and image/ground truth queues for data saving) were used to train the VHR images efficiently. Inference optimization was performed to speed up prediction in the release mode. To verify the efficiency of the proposed system, we used aerial image labeling from the Institut National de Recherche en Informatique et en Automatique (INRIA) and benchmarks from the Massachusetts Institute of Technology Aerial Imagery for Roof Segmentation (MITAIRS) to test the system performance and accuracy. Without the loss of accuracy, the S2S system improved prediction speed on the testing dataset by eight GPUs in a normal setting in both the INRIA dataset (from 534 to 72 s) and the MITAIRS dataset (818 to 120 s). With the prediction in half-float (using float-16 data), an 8-GPU parallel processing increased the speed to 38 s in the INRIA dataset and 83 s in the MITAIRS dataset. In a pressure test, our proposed system operated on 18,000 images with a size of 5000 × 5000 from 18.2 to 1.8 h with the prediction in full-float (using float-32 data) and 43 min with the prediction in half-float, increasing the speed by a factor of 9.78 and 25.3, respectively, when compared to system runs without optimization." @default.
- W4323543671 created "2023-03-09" @default.
- W4323543671 creator A5023786904 @default.
- W4323543671 creator A5025954012 @default.
- W4323543671 creator A5029816082 @default.
- W4323543671 creator A5043783761 @default.
- W4323543671 creator A5055493484 @default.
- W4323543671 date "2023-04-01" @default.
- W4323543671 modified "2023-10-15" @default.
- W4323543671 title "Space-to-speed architecture supporting acceleration on VHR image processing" @default.
- W4323543671 cites W2559597482 @default.
- W4323543671 cites W2620429297 @default.
- W4323543671 cites W2746501643 @default.
- W4323543671 cites W2883423620 @default.
- W4323543671 cites W2886934227 @default.
- W4323543671 cites W2956776634 @default.
- W4323543671 cites W2963136578 @default.
- W4323543671 cites W2963446712 @default.
- W4323543671 cites W2964217532 @default.
- W4323543671 cites W2964309882 @default.
- W4323543671 cites W2990392801 @default.
- W4323543671 cites W2994434065 @default.
- W4323543671 cites W3004492228 @default.
- W4323543671 cites W3007189272 @default.
- W4323543671 cites W3009818596 @default.
- W4323543671 cites W3019659794 @default.
- W4323543671 cites W3023120202 @default.
- W4323543671 cites W3083065220 @default.
- W4323543671 cites W3110908156 @default.
- W4323543671 cites W3175205795 @default.
- W4323543671 doi "https://doi.org/10.1016/j.isprsjprs.2023.02.010" @default.
- W4323543671 hasPublicationYear "2023" @default.
- W4323543671 type Work @default.
- W4323543671 citedByCount "2" @default.
- W4323543671 countsByYear W43235436712023 @default.
- W4323543671 crossrefType "journal-article" @default.
- W4323543671 hasAuthorship W4323543671A5023786904 @default.
- W4323543671 hasAuthorship W4323543671A5025954012 @default.
- W4323543671 hasAuthorship W4323543671A5029816082 @default.
- W4323543671 hasAuthorship W4323543671A5043783761 @default.
- W4323543671 hasAuthorship W4323543671A5055493484 @default.
- W4323543671 hasBestOaLocation W43235436711 @default.
- W4323543671 hasConcept C115961682 @default.
- W4323543671 hasConcept C146849305 @default.
- W4323543671 hasConcept C154945302 @default.
- W4323543671 hasConcept C173608175 @default.
- W4323543671 hasConcept C2779851693 @default.
- W4323543671 hasConcept C41008148 @default.
- W4323543671 hasConcept C68339613 @default.
- W4323543671 hasConcept C76155785 @default.
- W4323543671 hasConcept C79403827 @default.
- W4323543671 hasConcept C82876162 @default.
- W4323543671 hasConcept C9417928 @default.
- W4323543671 hasConceptScore W4323543671C115961682 @default.
- W4323543671 hasConceptScore W4323543671C146849305 @default.
- W4323543671 hasConceptScore W4323543671C154945302 @default.
- W4323543671 hasConceptScore W4323543671C173608175 @default.
- W4323543671 hasConceptScore W4323543671C2779851693 @default.
- W4323543671 hasConceptScore W4323543671C41008148 @default.
- W4323543671 hasConceptScore W4323543671C68339613 @default.
- W4323543671 hasConceptScore W4323543671C76155785 @default.
- W4323543671 hasConceptScore W4323543671C79403827 @default.
- W4323543671 hasConceptScore W4323543671C82876162 @default.
- W4323543671 hasConceptScore W4323543671C9417928 @default.
- W4323543671 hasFunder F4320321001 @default.
- W4323543671 hasLocation W43235436711 @default.
- W4323543671 hasOpenAccess W4323543671 @default.
- W4323543671 hasPrimaryLocation W43235436711 @default.
- W4323543671 hasRelatedWork W2021319666 @default.
- W4323543671 hasRelatedWork W2027972911 @default.
- W4323543671 hasRelatedWork W2058965144 @default.
- W4323543671 hasRelatedWork W2141978748 @default.
- W4323543671 hasRelatedWork W2146343568 @default.
- W4323543671 hasRelatedWork W2150291671 @default.
- W4323543671 hasRelatedWork W2164382479 @default.
- W4323543671 hasRelatedWork W2348330046 @default.
- W4323543671 hasRelatedWork W2764495645 @default.
- W4323543671 hasRelatedWork W98480971 @default.
- W4323543671 hasVolume "198" @default.
- W4323543671 isParatext "false" @default.
- W4323543671 isRetracted "false" @default.
- W4323543671 workType "article" @default.