A Dynamic Convolutional Layer for Short Range Weather Prediction

Benjamin Klein, Lior Wolf, Yehuda Afek; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 4840-4848

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Klein_2015_CVPR,
author = {Klein, Benjamin and Wolf, Lior and Afek, Yehuda},
title = {A Dynamic Convolutional Layer for Short Range Weather Prediction},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}