English

HyenaPixel: Global Image Context with Convolutions

Computer Vision and Pattern Recognition 2025-11-18 v2

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×\times191, 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.

Keywords

Cite

@article{arxiv.2402.19305,
  title  = {HyenaPixel: Global Image Context with Convolutions},
  author = {Julian Spravil and Sebastian Houben and Sven Behnke},
  journal= {arXiv preprint arXiv:2402.19305},
  year   = {2025}
}
R2 v1 2026-06-28T15:04:49.740Z