# Dense-Gated Blocks, towards layers relationships in densely connected blocks
_by Joseph Faye (IETR - Vaader) - 2021.03.18_
###### tags: `VAADER` `Reading Group`

## Abstract

<div style="text-align: justify">
ResNet [1], Highway networks [2] to DenseNet [3], adding more inter-layer connections besides the direct connection in adjacent layers, emerged as popular approaches to strengthen feature propagation among different layers. However, dense connections cause much redundancy especially in the case of DenseNet. Another aspect is that for many dense connections from previous layers, the role played by the mainstream module is unclear. To address these issues, authors introduce a gating mechanism, inspired by SENeT [4] to model the layer relationships in densely connected blocks.

[A Dense-Gated U-Net for Brain Lesion Segmentation](https://ieeexplore.ieee.org/abstract/document/9301852)
</div>

## Slides
{%pdf https://florianlemarchand.github.io/ressources/pdfs/VAADER_Reading_Group/2021-18-03-Faye-DenseGated.pdf %}

## Presentation and Discussions
<iframe src="https://videos.insa-rennes.fr/video/0156-vaader-reading-group-5-joseph-faye-dense-gated-blocks-towards-layers-relationships-in-densely-connected-blocks/?is_iframe=true" width="640" height="360" style="padding: 0; margin: 0; border:0" allowfullscreen ></iframe>

## Related Material
* [[1] Deep Residual Learning for Image Recognition (CVPR 2016)](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/He_Deep_Residual_Learning_CVPR_2016_paper.pdf)
* [[2] Highway Networks](https://arxiv.org/pdf/1505.00387.pdf)
* [[3] Densely Connected Convolutional Networks (CVPR 2017, Best Paper Award)](https://arxiv.org/abs/1608.06993)
* [[4] Squeeze-and-Excitation Networks (CVPR 2018)](https://arxiv.org/pdf/1709.01507.pdf)