@Article{CSIAM-AM-3-4,
author = {Zheng, Dihan and Chenglong, Bao and Zuoqiang, Shi and Ling, Haibin and Ma, Kaisheng},
title = {Unsupervised Deep Learning Meets Chan-Vese Model},
journal = {CSIAM Transactions on Applied Mathematics},
year = {2022},
volume = {3},
number = {4},
pages = {662--691},
abstract = {<p style="text-align: justify;">The Chan-Vese (CV) model is a classic region-based method in image segmentation. However, its piecewise constant assumption does not always hold for practical applications. Many improvements have been proposed but the issue is still far
from well solved. In this work, we propose an unsupervised image segmentation approach that integrates the CV model with deep neural networks, which significantly
improves the original CV model’s segmentation accuracy. Our basic idea is to apply
a deep neural network that maps the image into a latent space to alleviate the violation of the piecewise constant assumption in image space. We formulate this idea
under the classic Bayesian framework by approximating the likelihood with an evidence lower bound (ELBO) term while keeping the prior term in the CV model. Thus,
our model only needs the input image itself and does not require pre-training from
external datasets. Moreover, we extend the idea to multi-phase case and dataset based
unsupervised image segmentation. Extensive experiments validate the effectiveness
of our model and show that the proposed method is noticeably better than other unsupervised segmentation approaches.</p>},
issn = {2708-0579},
doi = {https://doi.org/10.4208/csiam-am.SO-2021-0049},
url = {https://global-sci.com/article/82331/unsupervised-deep-learning-meets-chan-vese-model}
}