C1 - Efficient biomedical image segmentation on Edge TPUs
Andreas M Kist, Michael Döllinger
Biomedical semantic segmentation is typically performed on dedicated, costly hardware. In a recent study, we suggested an optimized, tiny-weight U-Net for an inexpensive hardware accelerator, the Google Edge TPU. Using an open biomedical dataset for high-speed laryngeal videoendoscopy, we exemplarily show that we can dramatically reduce the parameter space and computations while keeping a high segmentation quality. Using a custom upsampling routine, we fully deployed optimized architectures to the Edge TPU. Combining the optimized architecture and the Edge TPU, we gain a total speedup of >79x compared to our initial baseline while keeping a high accuracy. This combination allows to provide immediate results at the point of care, especially in constrained computational environments.
Wednesday 7th July
C1-9 (short): Endoscopy and Validation Studies - 16:45 - 17:30 (UTC+2)