# Jointly Sparse Convolutional Neural Networks in Dual Spatial-Winograd Domains

Source: [Jointly Sparse Convolutional Neural Networks in Dual Spatial-Winograd Domains](<https://www.sota2.com/research/paper/68fa65651e209131cea09f3e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:25:53.160Z

Authors: Yoojin Choi, Mostafa El-Khamy, Jungwon Lee

Published: 2019-02-21T01:03:04.000Z

## Abstract

We consider the optimization of deep convolutional neural networks (CNNs) such that they provide good performance while having reduced complexity if deployed on either conventional systems with spatial-domain convolution or lower-complexity systems designed for Winograd convolution. The proposed framework produces one compressed model whose convolutional filters can be made sparse either in the spatial domain or in the Winograd domain. Hence, the compressed model can be deployed universally on any platform, without need for re-training on the deployed platform. To get a better compression ratio, the sparse model is compressed in the spatial domain that has a fewer number of parameters. From our experiments, we obtain $24.2\\times$ and $47.7\\times$ compressed models for ResNet-18 and AlexNet trained on the ImageNet dataset, while their computational cost is also reduced by $4.5\\times$ and $5.1\\times$, respectively.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1902.08192>)

[PDF](<https://arxiv.org/pdf/1902.08192.pdf>)