@inproceedings{SpravilHoubenBehnke2024,
  author    = {Spravil, Julian and Houben, Sebastian and Behnke, Sven},
  title     = {HyenaPixel: Global Image Context with Convolutions},
  booktitle = {Endriss, Melo et al. (Eds.): ECAI 2024, 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain},
  isbn      = {978-1-64368-548-9},
  doi       = {10.3233/FAIA240529},
  institution = {Fachbereich Informatik},
  pages     = {521 -- 528},
  year      = {2024},
  abstract  = {In computer vision, a larger effective receptive field (ERF) is associated with better performance. While attention natively supports global context, its quadratic complexity limits its applicability to tasks that benefit from high-resolution input. In this work, we extend Hyena, a convolution-based attention replacement, from causal sequences to bidirectional data and two-dimensional image space. We scale Hyena's convolution kernels beyond the feature map size, up to 191×191, to maximize ERF while maintaining sub-quadratic complexity in the number of pixels. We integrate our two-dimensional Hyena, HyenaPixel, and bidirectional Hyena into the MetaFormer framework. For image categorization, HyenaPixel and bidirectional Hyena achieve a competitive ImageNet-1k top-1 accuracy of 84.9\% and 85.2\%, respectively, with no additional training data, while outperforming other convolutional and large-kernel networks. Combining HyenaPixel with attention further improves accuracy. We attribute the success of bidirectional Hyena to learning the data-dependent geometric arrangement of pixels without a fixed neighborhood definition. Experimental results on downstream tasks suggest that HyenaPixel with large filters and a fixed neighborhood leads to better localization performance.},
  language  = {en}
}