Feedback Attention for Cell Image Segmentation
Abstract
In this paper, we address cell image segmentation task by Feedback Attention mechanism like feedback processing. Unlike conventional neural network models of feedforward processing, we focused on the feedback processing in human brain and assumed that the network learns like a human by connecting feature maps from deep layers to shallow layers. We propose some Feedback Attentions which imitate human brain and feeds back the feature maps of output layer to close layer to the input. U-Net with Feedback Attention showed better result than the conventional methods using only feedforward processing.
Cite
Text
Tsuda et al. "Feedback Attention for Cell Image Segmentation." European Conference on Computer Vision Workshops, 2020. doi:10.1007/978-3-030-66415-2_24Markdown
[Tsuda et al. "Feedback Attention for Cell Image Segmentation." European Conference on Computer Vision Workshops, 2020.](https://mlanthology.org/eccvw/2020/tsuda2020eccvw-feedback/) doi:10.1007/978-3-030-66415-2_24BibTeX
@inproceedings{tsuda2020eccvw-feedback,
title = {{Feedback Attention for Cell Image Segmentation}},
author = {Tsuda, Hiroki and Shibuya, Eisuke and Hotta, Kazuhiro},
booktitle = {European Conference on Computer Vision Workshops},
year = {2020},
pages = {365-379},
doi = {10.1007/978-3-030-66415-2_24},
url = {https://mlanthology.org/eccvw/2020/tsuda2020eccvw-feedback/}
}