# Accelerating Large Kernel Convolutions with Nested Winograd Transformation.pdf

arXiv: https://arxiv.org/abs/2102.13272 · HTML: https://mlsanity.com/paper/2102.13272/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 21 references that are in the map.
- First posted on arXiv 26 Feb 2021.

## Builds on (most cited first, 5 of 5)

- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [Progressive Neural Architecture Search](https://mlsanity.com/paper/1712.00559/) (2017)
- [Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network](https://mlsanity.com/paper/1703.02719/) (2017)
- [Fast Algorithms for Convolutional Neural Networks](https://mlsanity.com/paper/1509.09308/) (2015)
- [Deep Tensor Convolution on Multicores](https://mlsanity.com/paper/1611.06565/) (2016)

## Built on by (most cited first, 1 of 1)

- [Fast Convolution based on Winograd Minimum Filtering: Introduction and Development](https://mlsanity.com/paper/2111.00977/) (2021)

## Abstract (arXiv)

Recent literature has shown that convolutional neural networks (CNNs) with large kernels outperform vision transformers (ViTs) and CNNs with stacked small kernels in many computer vision tasks, such as object detection and image restoration. The Winograd transformation helps reduce the number of repetitive multiplications in convolution and is widely supported by many commercial AI processors. Researchers have proposed accelerating large kernel convolutions by linearly decomposing them into many small kernel convolutions and then sequentially accelerating each small kernel convolution with the Winograd algorithm. This work proposes a nested Winograd algorithm that iteratively decomposes a large kernel convolution into small kernel convolutions and proves it to be more effective than the linear decomposition Winograd transformation algorithm. Experiments show that compared to the linear decomposition Winograd algorithm, the proposed algorithm reduces the total number of multiplications by 1.4 to 10.5 times for computing 4x4 to 31x31 convolutions.