Semantic Segmentation with Labeling Uncertainty and Class Imbalance
Abstract
Recently, methods based on Convolutional Neural Networks (CNN) achieved impressive success in semantic segmentation tasks. However, challenges such as the class imbalance and the uncertainty in the pixel-labeling process are not completely addressed. As such, we present a new approach that calculates a weight for each pixel considering its class and uncertainty during the labeling process. The pixel-wise weights are used during training to increase or decrease the importance of the pixels. Experimental results show that the proposed approach leads to significant improvements in three challenging segmentation tasks in comparison to baseline methods. It was also proved to be more invariant to noise. The approach presented here may be used within a wide range of semantic segmentation methods to improve their robustness.
Cite
@article{arxiv.2102.04566,
title = {Semantic Segmentation with Labeling Uncertainty and Class Imbalance},
author = {Patrik Olã Bressan and José Marcato Junior and José Augusto Correa Martins and Diogo Nunes Gonçalves and Daniel Matte Freitas and Lucas Prado Osco and Jonathan de Andrade Silva and Zhipeng Luo and Jonathan Li and Raymundo Cordero Garcia and Wesley Nunes Gonçalves},
journal= {arXiv preprint arXiv:2102.04566},
year = {2022}
}
Comments
15 pages, 9 figures, 3 tables