Scaling Up Computer Vision Neural Networks Using Fast Fourier Transform
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 9 of its 10 references that are in the map. First posted on arXiv 2 Feb 2023.
Builds on
9 of 10 references.
References · 9
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
- 2016Layer Normalizationcited by 5,669
- 2022A ConvNet for the 2020scited by 3,579
- 2020Long Range Arena: A Benchmark for Efficient Transformerscited by 700
- 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 605
- 2022On the Parameterization and Initialization of Diagonal State Space Modelscited by 424
- 2021FNet: Mixing Tokens with Fourier Transformscited by 347
- 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
- 2022What Makes Convolutional Models Great on Long Sequence Modeling?cited by 87
Built on by
Not cited yet.