Details

Autor(en) / Beteiligte

• Kwak, Jaeho
• Yu, Hyunwoo
• Cho, Yubin
• Kang, Sukju
• Cho, Jaechan
• Park, Jun-Young
• Lee, Ji-Won

Titel

Deep Learning-based Real-time Segmentation for Edge Computing Devices

Ist Teil von

• 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS), 2022, p.1-1

Ort / Verlag

IEEE

Erscheinungsjahr

2022

Quelle

IEEE/IET Electronic Library (IEL)

Beschreibungen/Notizen

• Recently, due to the rapid improvement of artificial intelligence technology, numerous studies are considered to solve various problems using deep learning. Typical deep neural networks for semantic segmentation require the high computation with a large capacity to extract abundant amounts of contextual information for accurate prediction. Our live demonstration will show real-time semantic segmentation operation on an NVIDIA Jetson-Xavier board with the BiSeNet-based method compressed using a novel knowledge distillation method.