We design a new connectivity pattern for the U-Net architecture. Given several stacked U-Nets, we couple each U-Net pair through the connections of their semantic blocks, resulting in the coupled U-Nets (CU-Net). The coupling connections could make the information flow more efficiently across U-Nets. The feature reuse across U-Nets makes each U-Net very parameter efficient. We evaluate the coupled U-Nets on two benchmark datasets of human pose estimation. Both the accuracy and model parameter number are compared. The CU-Net obtains comparable accuracy as state-of-the-art methods. However, it only has at least 60% fewer parameters than other approaches.
@article{arxiv.1808.06521,
title = {CU-Net: Coupled U-Nets},
author = {Zhiqiang Tang and Xi Peng and Shijie Geng and Yizhe Zhu and Dimitris N. Metaxas},
journal= {arXiv preprint arXiv:1808.06521},
year = {2018}
}