TY  - CPAPER
U1  - Konferenzveröffentlichung
A1  - Spravil, Julian
A1  - Houben, Sebastian
A1  - Behnke, Sven
T1  - HyenaPixel: Global Image Context with Convolutions
T2  - Endriss, Melo et al. (Eds.): ECAI 2024, 27th European Conference on Artificial Intelligence, 19–24 October 2024, Santiago de Compostela, Spain
N2  - 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.
Y1  - 2024
UN  - https://nbn-resolving.org/urn:nbn:de:hbz:1044-opus-86391
SN  - 978-1-64368-548-9
SB  - 978-1-64368-548-9
U6  - https://doi.org/10.3233/FAIA240529
DO  - https://doi.org/10.3233/FAIA240529
SP  - 521
EP  - 528
S1  - 8
PB  - IOS Press
CY  - Amsterdam
ER  -