SelectionConv: Convolutional Neural Networks for Non-Rectilinear Image Data
Abstract
Convolutional Neural Networks have revolutionized vision applications. There are image domains and representations, however, that cannot be handled by standard CNNs (e.g., spherical images, superpixels). Such data are usually processed using networks and algorithms specialized for each type. In this work, we show that it may not always be necessary to use specialized neural networks to operate on such spaces. Instead, we introduce a new structured graph convolution operator that can copy 2D convolution weights, transferring the capabilities of already trained traditional CNNs to our new graph network. This network can then operate on any data that can be represented as a positional graph. By converting non-rectilinear data to a graph, we can apply these convolutions on these irregular image domains without requiring training on large domain-specific datasets.
Cite
Text
Hart et al. "SelectionConv: Convolutional Neural Networks for Non-Rectilinear Image Data." Proceedings of the European Conference on Computer Vision (ECCV), 2022. doi:10.1007/978-3-031-20071-7_19Markdown
[Hart et al. "SelectionConv: Convolutional Neural Networks for Non-Rectilinear Image Data." Proceedings of the European Conference on Computer Vision (ECCV), 2022.](https://mlanthology.org/eccv/2022/hart2022eccv-selectionconv/) doi:10.1007/978-3-031-20071-7_19BibTeX
@inproceedings{hart2022eccv-selectionconv,
title = {{SelectionConv: Convolutional Neural Networks for Non-Rectilinear Image Data}},
author = {Hart, David and Whitney, Michael and Morse, Bryan},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2022},
doi = {10.1007/978-3-031-20071-7_19},
url = {https://mlanthology.org/eccv/2022/hart2022eccv-selectionconv/}
}