Semantic Segmentation with Scarce Data

Research output: Working paper › Preprint › Research

Standard

Semantic Segmentation with Scarce Data. / Belongie, Serge; Katsman, Isay; Tripathi, Rohun; Velt, Andreas.

2018.

Research output: Working paper › Preprint › Research

Harvard

Belongie, S, Katsman, I, Tripathi, R & Velt, A 2018 'Semantic Segmentation with Scarce Data'. <https://vision.cornell.edu/se3/wp-content/uploads/2018/07/icml-four-page.pdf>

APA

Belongie, S., Katsman, I., Tripathi, R., & Velt, A. (2018). Semantic Segmentation with Scarce Data. https://vision.cornell.edu/se3/wp-content/uploads/2018/07/icml-four-page.pdf

Vancouver

Belongie S, Katsman I, Tripathi R, Velt A. Semantic Segmentation with Scarce Data. 2018 Aug 2.

Author

Belongie, Serge ; Katsman, Isay ; Tripathi, Rohun ; Velt, Andreas. / Semantic Segmentation with Scarce Data. 2018.

Bibtex

@techreport{37fb30003c8f43238174a194646df4cd,
title = "Semantic Segmentation with Scarce Data",
abstract = "Semantic segmentation is a challenging vision problem that usually necessitates the collection of large amounts of finely annotated data, which is often quite expensive to obtain. Coarsely annotated data provides an interesting alternative as it is usually substantially more cheap. In this work, we present a method to leverage coarsely annotated data along with fine supervision to produce better segmentation results than would be obtained when training using only the fine data. We validate our approach by simulating a scarce data setting with less than 200 low resolution images from the Cityscapes dataset and show that our method substantially outperforms solely training on the fine annotation data by an average of 15.52% mIoU and outperforms the coarse mask by an average of 5.28% mIoU.",
author = "Serge Belongie and Isay Katsman and Rohun Tripathi and Andreas Velt",
year = "2018",
month = aug,
day = "2",
language = "English",
type = "WorkingPaper",

}

RIS

TY - UNPB

T1 - Semantic Segmentation with Scarce Data

AU - Belongie, Serge

AU - Katsman, Isay

AU - Tripathi, Rohun

AU - Velt, Andreas

PY - 2018/8/2

Y1 - 2018/8/2

N2 - Semantic segmentation is a challenging vision problem that usually necessitates the collection of large amounts of finely annotated data, which is often quite expensive to obtain. Coarsely annotated data provides an interesting alternative as it is usually substantially more cheap. In this work, we present a method to leverage coarsely annotated data along with fine supervision to produce better segmentation results than would be obtained when training using only the fine data. We validate our approach by simulating a scarce data setting with less than 200 low resolution images from the Cityscapes dataset and show that our method substantially outperforms solely training on the fine annotation data by an average of 15.52% mIoU and outperforms the coarse mask by an average of 5.28% mIoU.

AB - Semantic segmentation is a challenging vision problem that usually necessitates the collection of large amounts of finely annotated data, which is often quite expensive to obtain. Coarsely annotated data provides an interesting alternative as it is usually substantially more cheap. In this work, we present a method to leverage coarsely annotated data along with fine supervision to produce better segmentation results than would be obtained when training using only the fine data. We validate our approach by simulating a scarce data setting with less than 200 low resolution images from the Cityscapes dataset and show that our method substantially outperforms solely training on the fine annotation data by an average of 15.52% mIoU and outperforms the coarse mask by an average of 5.28% mIoU.

UR - https://arxiv.org/abs/1807.00911

M3 - Preprint

BT - Semantic Segmentation with Scarce Data

ER -

ID: 306931672