Residual Inception Skip Network for Binary Segmentation

Jigar Doshi; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 216-219

Abstract


This paper summarizes our approach to the Deep GlobeRoad Extraction challenge 2018. In this challenge, we are tasked to find road networks from satellite images. First, we explain our U-Net type baseline model for the challenge. Second, we explain a new architecture that takes in the lessons from some of the popular approaches that we call Residual Inception Skip Net. Finally, we outline our cyclic learning rate based ensembling approach which improved the overall single model performance and the final solution for submission. Our final model increases the IoU by 3 points over the baseline.

Related Material


[pdf]
[bibtex]
@InProceedings{Doshi_2018_CVPR_Workshops,
author = {Doshi, Jigar},
title = {Residual Inception Skip Network for Binary Segmentation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2018}
}