Picture for Gulnur Selda Uyanik

Gulnur Selda Uyanik

L^3U-net: Low-Latency Lightweight U-net Based Image Segmentation Model for Parallel CNN Processors

Add code
Mar 30, 2022
Osman Erman Okman, Mehmet Gorkem Ulkar, Gulnur Selda Uyanik
Figure 1 for L^3U-net: Low-Latency Lightweight U-net Based Image Segmentation Model for Parallel CNN Processors
Figure 2 for L^3U-net: Low-Latency Lightweight U-net Based Image Segmentation Model for Parallel CNN Processors
Figure 3 for L^3U-net: Low-Latency Lightweight U-net Based Image Segmentation Model for Parallel CNN Processors
Figure 4 for L^3U-net: Low-Latency Lightweight U-net Based Image Segmentation Model for Parallel CNN Processors

In this research, we propose a tiny image segmentation model, L^3U-net, that works on low-resource edge devices in real-time. We introduce a data folding technique that reduces inference latency by leveraging the parallel convolutional layer processing capability of the CNN accelerators. We also deploy the proposed model to such a device, MAX78000, and the results show that L^3U-net achieves more than 90% accuracy over two different segmentation datasets with 10 fps.

Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon