SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.07476 · 2019

An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Assigning a label to each pixel in an image, namely semantic segmentation, has been an important task in computer vision, and has applications in autonomous driving, robotic navigation, localization, and scene understanding. Fully convolutional neural networks have proved to be a successful solution for the task over the years but most of the work being done focuses primarily on accuracy. In this paper, we present a computationally efficient approach to semantic segmentation, while achieving a high mean intersection over union (mIOU), 70.33% on Cityscapes challenge. The network proposed is capable of running real-time on mobile devices. In addition, we make our code and model weights publicly available.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1902.07476")
get_code_for_paper("1902.07476")
have("1902.07476")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1902.07476.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1902.07476.svg)](https://syntology.ai/paper/1902.07476)

Connect an agent — have() is free.