TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Semantic Segmentation	Cityscapes test	ESPNet	Mean IoU (class)	60.3%	# 98
Semantic Segmentation	PASCAL VOC 2012 test	ESPNet	Mean IoU	63.01%	# 48

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/espnet-efficient-spatial-pyramid-of-dilated/semantic-segmentation-on-pascal-voc-2012)](https://paperswithcode.com/sota/semantic-segmentation-on-pascal-voc-2012?p=espnet-efficient-spatial-pyramid-of-dilated)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/espnet-efficient-spatial-pyramid-of-dilated/semantic-segmentation-on-cityscapes)](https://paperswithcode.com/sota/semantic-segmentation-on-cityscapes?p=espnet-efficient-spatial-pyramid-of-dilated)`

ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

ECCV 2018 · Sachin Mehta, Mohammad Rastegari, Anat Caspi, Linda Shapiro, Hannaneh Hajishirzi ·

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 ESPNet 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.