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 dep...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-03
Main Authors: Osman Erman Okman, Ulkar, Mehmet Gorkem, Uyanik, Gulnur Selda
Format: Article
Language:English
Subjects:
Image segmentation
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422