Condensed U-Net (CU-Net): An Improved U-Net Architecture for Cell Segmentation Powered by 4x4 Max-Pooling Layers

Logo poskytovatele
Logo poskytovatele

Varování

Publikace nespadá pod Filozofickou fakultu, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.
Autoři

AKBAS Cem Emre KOZUBEK Michal

Rok publikování 2020
Druh Článek ve sborníku
Konference IEEE 17th International Symposium on Biomedical Imaging
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
www https://ieeexplore.ieee.org/abstract/document/9098351
Doi http://dx.doi.org/10.1109/ISBI45749.2020.9098351
Klíčová slova Biomedical Image Segmentation; Convolutional Neural Networks; Deep Learning; Feature Learning; Max Pooling
Popis Recently, the U-Net has been the dominant approach in the cell segmentation task in biomedical images due to its success in a wide range of image recognition tasks. However, recent studies did not focus enough on updating the architecture of the U-Net and designing specialized loss functions for bioimage segmentation. We show that the U-Net architecture can achieve more successful results with efficient architectural improvements. We propose a condensed encoder-decoder scheme that employs the 4x4 max-pooling operation and triple convolutional layers. The proposed network architecture is trained using a novel combined loss function specifically designed for bioimage segmentation. On the benchmark datasets from the Cell Tracking Challenge, the experimental results show that the proposed cell segmentation system outperforms the U-Net.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.