Computer vision applications for UAVs often rely on deep neural networks (DNNs) to increase prediction accu- racy. As such DNNs crave for computational resources that can be hardly matched by those available at the UAVs, an emerging solution is to split the DNN into a low-complexity head model run at the UAV and a heavier tail run at the edge. This approach, however, comes at the cost of transmitting a large tensor data, hence of high bandwidth consumption, on the UAV-edge radio link. We tackle this problem by proposing the Compressed Tensor-based DNN split (CoTeD) framework, which executes tensor compression at the UAV and reconstruction at the edge, while conveniently trading off tensor compression with quality of the computer vision task output. When compared with the no-split case, CoTeD reduces the UAV computational burden by 50% w.r.t. performing inference at the UAV only, and the amount of transmitted data by over one order of magnitude w.r.t. running inference at the edge only. When compared to compressive sensing, JPEG-100, and the whole DNN run at the edge, CoTeD decreases the overall latency by (resp.) 95%, 75%, and 80%.
Tensor Compression and Reconstruction in Split DNN for Real-time Object Detection at the Edge / Yu, YEN-CHIA; Levorato, Marco; Chiasserini, Carla Fabiana. - ELETTRONICO. - (2024). (Intervento presentato al convegno 2024 IEEE International Mediterranean Conference on Communications and Networking (MeditCom) tenutosi a Madrid (Spain) nel 08-11 July 2024) [10.1109/MeditCom61057.2024.10621382].
Tensor Compression and Reconstruction in Split DNN for Real-time Object Detection at the Edge
Yenchia Yu;Marco Levorato;Carla Fabiana Chiasserini
2024
Abstract
Computer vision applications for UAVs often rely on deep neural networks (DNNs) to increase prediction accu- racy. As such DNNs crave for computational resources that can be hardly matched by those available at the UAVs, an emerging solution is to split the DNN into a low-complexity head model run at the UAV and a heavier tail run at the edge. This approach, however, comes at the cost of transmitting a large tensor data, hence of high bandwidth consumption, on the UAV-edge radio link. We tackle this problem by proposing the Compressed Tensor-based DNN split (CoTeD) framework, which executes tensor compression at the UAV and reconstruction at the edge, while conveniently trading off tensor compression with quality of the computer vision task output. When compared with the no-split case, CoTeD reduces the UAV computational burden by 50% w.r.t. performing inference at the UAV only, and the amount of transmitted data by over one order of magnitude w.r.t. running inference at the edge only. When compared to compressive sensing, JPEG-100, and the whole DNN run at the edge, CoTeD decreases the overall latency by (resp.) 95%, 75%, and 80%.File | Dimensione | Formato | |
---|---|---|---|
Rex_Marco-2.pdf
accesso aperto
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
PUBBLICO - Tutti i diritti riservati
Dimensione
424.37 kB
Formato
Adobe PDF
|
424.37 kB | Adobe PDF | Visualizza/Apri |
Chisserini-Tensor.pdf
non disponibili
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
685.52 kB
Formato
Adobe PDF
|
685.52 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2988278