Method Details

Details for method 'ESPNet'

name	ESPNet
challenge	pixel-level semantic labeling
details	We introduce a fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints. ESPNet is based on a new convolutional module, efficient spatial pyramid (ESP), which is efficient in terms of computation, memory, and power. ESPNet is 22 times faster (on a standard GPU) and 180 times smaller than the state-of-the-art semantic segmentation network PSPNet, while its category-wise accuracy is only 8% less. We evaluated EPSNet on a variety of semantic segmentation datasets including Cityscapes, PASCAL VOC, and a breast biopsy whole slide image dataset. Under the same constraints on memory and computation, ESPNet outperforms all the current efficient CNN networks such as MobileNet, ShuffleNet, and ENet on both standard metrics and our newly introduced performance metrics that measure efficiency on edge devices. Our network can process high resolution images at a rate of 112 and 9 frames per second on a standard GPU and edge device, respectively
publication	ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation Sachin Mehta, Mohammad Rastegari, Anat Caspi, Linda Shapiro, and Hannaneh Hajishirzi https://arxiv.org/abs/1803.06815
project page / code	https://sacmehta.github.io/ESPNet/
used Cityscapes data	fine annotations
used external data
runtime	0.0089 s TitanX
subsampling	2
submission date	January, 2018
previous submissions