Feature Pyramid Network with ResNext backbone implemented in Keras. Use this for semantic segmentation tasks. Probably a good first step to get you up on those Kaggle competitions where everyone is still using regular Resnet FCNs ;)
Check the "Aggregated Residual Transformations for Deep Neural Networks" paper for info on ResNext
@article{DBLP:journals/corr/XieGDTH16,
author = {Saining Xie and
Ross B. Girshick and
Piotr Doll{\'{a}}r and
Zhuowen Tu and
Kaiming He},
title = {Aggregated Residual Transformations for Deep Neural Networks},
journal = {CoRR},
volume = {abs/1611.05431},
year = {2016},
url = {https://arxiv.org/abs/1611.05431},
archivePrefix = {arXiv},
eprint = {1611.05431},
timestamp = {Mon, 13 Aug 2018 16:45:58 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/XieGDTH16},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
and "Feature Pyramid Networks for Object Detection" for info on FPNs:
@article{DBLP:journals/corr/LinDGHHB16,
author = {Tsung{-}Yi Lin and
Piotr Doll{\'{a}}r and
Ross B. Girshick and
Kaiming He and
Bharath Hariharan and
Serge J. Belongie},
title = {Feature Pyramid Networks for Object Detection},
journal = {CoRR},
volume = {abs/1612.03144},
year = {2016},
url = {https://arxiv.org/abs/1612.03144},
archivePrefix = {arXiv},
eprint = {1612.03144},
timestamp = {Mon, 13 Aug 2018 16:48:50 +0200},
biburl = {https://dblp.org/rec/bib/journals/corr/LinDGHHB16},
bibsource = {dblp computer science bibliography, https://dblp.org}
}