We present an efficient alternative to the convolutional layer using cheap spatial transformations. This construction exploits an inherent spatial redundancy of the learned convolutional filters to enable a much greater parameter efficiency, while maintaining the top-end accuracy of their dense counter-parts. Training these networks is modelled as a generalised pruning problem, whereby the pruned filters are replaced with cheap transformations from the set of non-pruned filters. We provide an efficient implementation of the proposed layer, followed by two natural extensions to avoid excessive feature compression and to improve the expressivity of the transformed features. We show that these networks can achieve comparable or improved performance to state-of-the-art pruning models across both the CIFAR-10 and ImageNet-1K datasets.

翻译：我们提出了一种利用廉价空间变换替代卷积层的高效方案。该结构充分利用了学习所得卷积滤波器固有的空间冗余性，在保持与密集卷积网络同等顶尖精度的同时，实现了显著更高的参数效率。此类网络的训练被建模为广义剪枝问题：被剪枝的滤波器通过非剪枝滤波器集合中的廉价变换进行替换。我们给出了所提层的高效实现方案，并提出了两项自然扩展以避免过度特征压缩并提升变换后特征的表征能力。实验表明，在CIFAR-10和ImageNet-1K数据集上，这些网络能够达到或超越现有最佳剪枝模型的性能。