EdgeSegNet: A Compact Network for Semantic Segmentation
arXiv:1905.04222
Abstract
In this study, we introduce EdgeSegNet, a compact deep convolutional neural network for the task of semantic segmentation. A human-machine collaborative design strategy is leveraged to create EdgeSegNet, where principled network design prototyping is coupled with machine-driven design exploration to create networks with customized module-level macroarchitecture and microarchitecture designs tailored for the task. Experimental results showed that EdgeSegNet can achieve semantic segmentation accuracy comparable with much larger and computationally complex networks (>20x} smaller model size than RefineNet) as well as achieving an inference speed of ~38.5 FPS on an NVidia Jetson AGX Xavier. As such, the proposed EdgeSegNet is well-suited for low-power edge scenarios.
5 pages
References in corpus (5)
- Distilling the Knowledge in a Neural Network
- Rethinking Atrous Convolution for Semantic Image Segmentation
- ProjectionNet: Learning Efficient On-Device Deep Networks Using Neural Projections
- Two-Bit Networks for Deep Learning on Resource-Constrained Embedded Devices
- SquishedNets: Squishing SqueezeNet further for edge device scenarios via deep evolutionary synthesis