Abstract
In this work, we have investigated various style transfer approaches and (i) examined how the stylized reconstruction changes with the change of loss function and (ii) provided a computationally efficient solution for the same. We have used elegant techniques like depth-wise separable convolution in place of convolution and nearest neighbor interpolation in place of transposed convolution. Further, we have also added multiple interpolations in place of transposed convolution. The results obtained are perceptually similar in quality, while being computationally very efficient. The decrease in the computational complexity of our architecture is validated by the decrease in the testing time by 26.1%, 39.1%, and 57.1%, respectively.
Abstract (translated)
在这项工作中，我们研究了各种风格转移方法，并且（i）研究了风格化重建如何随着损失函数的变化而变化，以及（ii）为此提供了计算上有效的解决方案。我们使用了深度可分离卷积等优雅技术代替卷积和最近邻插值来代替转置卷积。此外，我们还添加了多个插值来代替转置卷积。获得的结果在感知上在质量上相似，而在计算上非常有效。我们的架构的计算复杂性的降低通过测试时间分别减少26.1％，39.1％和57.1％来验证。
URL
https://arxiv.org/abs/1807.05927
