A Dynamic Convolutional Layer for Short Range Weather Prediction
Abstract
We present a new deep network layer called ``Dynamic Convolutional Layer" which is a generalization of the convolutional layer. The conventional convolutional layer uses filters that are learned during training and are held constant during testing. In contrast, the dynamic convolutional layer uses filters that will vary from input to input during testing. This is achieved by learning a function that maps the input to the filters. We apply the dynamic convolutional layer to the application of short range weather prediction and show performance improvements compared to other baselines.
Cite
Text
Klein et al. "A Dynamic Convolutional Layer for Short Range Weather Prediction." Conference on Computer Vision and Pattern Recognition, 2015.Markdown
[Klein et al. "A Dynamic Convolutional Layer for Short Range Weather Prediction." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/klein2015cvpr-dynamic/)BibTeX
@inproceedings{klein2015cvpr-dynamic,
title = {{A Dynamic Convolutional Layer for Short Range Weather Prediction}},
author = {Klein, Benjamin and Wolf, Lior and Afek, Yehuda},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2015},
url = {https://mlanthology.org/cvpr/2015/klein2015cvpr-dynamic/}
}