Walking on Two Legs: Learning Image Segmentation with Noisy Labels
Guohua Cheng, Hongli Ji, Yan Tian
Abstract
Image segmentation automatically segments a target object in an image and has recently achieved prominent progress due to the development of deep convolutional neural networks (DCNNs). However, the quality of manual labels plays an essential role in the segmentation accuracy, while in practice it could vary a lot and in turn could substantially mislead the training process and limit the effectiveness. In this paper, we propose a novel label refinement and sample reweighting method, and a novel generative adversarial network (GAN) is introduced to fuse these two models into an integrated framework. We evaluate our approach on the publicly available datasets, and the results show our approach to be competitive when compared with other state-of-the-art approaches dealing with the noisy labels in image segmentation.
BibTeX
@InProceedings{pmlr-v124-cheng20a,
title = {Walking on Two Legs: Learning Image Segmentation with Noisy Labels},
author = {Cheng, Guohua and Ji, Hongli and Tian, Yan},
booktitle = {Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI)},
pages = {330--339},
year = {2020},
editor = {Peters, Jonas and Sontag, David},
volume = {124},
series = {Proceedings of Machine Learning Research},
month = {03--06 Aug},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v124/cheng20a/cheng20a.pdf},
url = {https://proceedings.mlr.press/v124/cheng20a.html},
abstract = {Image segmentation automatically segments a target object in an image and has recently achieved prominent progress due to the development of deep convolutional neural networks (DCNNs). However, the quality of manual labels plays an essential role in the segmentation accuracy, while in practice it could vary a lot and in turn could substantially mislead the training process and limit the effectiveness. In this paper, we propose a novel label refinement and sample reweighting method, and a novel generative adversarial network (GAN) is introduced to fuse these two models into an integrated framework. We evaluate our approach on the publicly available datasets, and the results show our approach to be competitive when compared with other state-of-the-art approaches dealing with the noisy labels in image segmentation.}
}