Search Results for author:
Found 1 papers, 0 papers with code
HyenaPixel: Global Image Context with Convolutions
For image categorization, HyenaPixel and bidirectional Hyena achieve a competitive ImageNet-1k top-1 accuracy of 83. 0% and 83. 5%, respectively, while outperforming other large-kernel networks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
