Papers
arxiv:2402.19305

HyenaPixel: Global Image Context with Convolutions

Published on Feb 29
Authors:

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 191times191, 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.

Community

Sign up or log in to comment

Models citing this paper 8

Browse 8 models citing this paper

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2402.19305 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2402.19305 in a Space README.md to link it from this page.

Collections including this paper 2