0

Scaling Up Computer Vision Neural Networks Using Fast Fourier Transform

Fast Fourier Transform is employed to address scaling challenges in Convolutional Neural Networks with larger kernels and Vision Transformers with quadratic complexity for high-resolution images.

Year
2023
Venue
arXiv 2023
Authors
1
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2302.12185ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

Deep Learning-based Computer Vision field has recently been trying to explore larger kernels for convolution to effectively scale up Convolutional Neural Networks. Simultaneously, new paradigm of models such as Vision Transformers find it difficult to scale up to larger higher resolution images due to their quadratic complexity in terms of input sequence. In this report, Fast Fourier Transform is utilised in various ways to provide some solutions to these issues.

Authors

1