As the saying goes, sometimes less is more -- and when it comes to neural networks, that couldn't be more true. Enter pruning, the art of selectively trimming away unnecessary parts of a network to create a more streamlined, efficient architecture. In this paper, we introduce a novel end-to-end pipeline for model pruning via the frequency domain. This work aims to shed light on the interoperability of intermediate model outputs and their significance beyond the spatial domain. Our method, dubbed Common Frequency Domain Pruning (CFDP) aims to extrapolate common frequency characteristics defined over the feature maps to rank the individual channels of a layer based on their level of importance in learning the representation. By harnessing the power of CFDP, we have achieved state-of-the-art results on CIFAR-10 with GoogLeNet reaching an accuracy of 95.25%, that is, +0.2% from the original model. We also outperform all benchmarks and match the original model's performance on ImageNet, using only 55% of the trainable parameters and 60% of the FLOPs. In addition to notable performances, models produced via CFDP exhibit robustness to a variety of configurations including pruning from untrained neural architectures, and resistance to adversarial attacks. The implementation code can be found at https://github.com/Skhaki18/CFDP.

翻译：[translated abstract in Chinese] 常言道，少即是多——对于神经网络而言，这一点尤为贴切。剪枝，作为一门选择性修剪网络冗余部分以构建更精简、高效架构的艺术，应运而生。本文提出一种新颖的基于频域的端到端模型剪枝流水线。本研究旨在揭示中间模型输出的可交互性及其在空间域之外的重要性。我们提出的方法，即公共频率域剪枝（CFDP），旨在推断特征映射上定义的公共频率特征，从而根据各通道在学习表征中的重要程度对层的通道进行排序。借助CFDP的强大功能，我们在CIFAR-10数据集上使用GoogLeNet达到了95.25%的准确率，即比原始模型高出0.2%，取得了当前最优结果。同时，在ImageNet数据集上，我们仅使用55%的可训练参数和60%的浮点运算量，便超越了所有基准方法并匹配了原始模型的性能。除显著性能外，通过CFDP生成的模型对多种配置表现出鲁棒性，包括从未经训练的神经架构进行剪枝以及抵御对抗攻击。实现代码请参见：https://github.com/Skhaki18/CFDP。