Convolutional neural networks (CNNs) have shown state-of-the-art performance in various applications. However, CNNs are resource-hungry due to their requirement of high computational complexity and memory storage. Recent efforts toward achieving computational efficiency in CNNs involve filter pruning methods that eliminate some of the filters in CNNs based on the \enquote{importance} of the filters. The majority of existing filter pruning methods are either "active", which use a dataset and generate feature maps to quantify filter importance, or "passive", which compute filter importance using entry-wise norm of the filters without involving data. Under a high pruning ratio where large number of filters are to be pruned from the network, the entry-wise norm methods eliminate relatively smaller norm filters without considering the significance of the filters in producing the node output, resulting in degradation in the performance. To address this, we present a passive filter pruning method where the filters are pruned based on their contribution in producing output by considering the operator norm of the filters. The proposed pruning method generalizes better across various CNNs compared to that of the entry-wise norm-based pruning methods. In comparison to the existing active filter pruning methods, the proposed pruning method is at least 4.5 times faster in computing filter importance and is able to achieve similar performance compared to that of the active filter pruning methods. The efficacy of the proposed pruning method is evaluated on audio scene classification and image classification using various CNNs architecture such as VGGish, DCASE21_Net, VGG-16 and ResNet-50.

翻译：卷积神经网络（CNNs）在各类应用中展现出最先进的性能。然而，由于其高计算复杂度和内存存储需求，CNNs对资源消耗较大。近期提升CNNs计算效率的研究包括滤波器剪枝方法，这些方法基于滤波器的"重要性"来消除部分滤波器。现有大多数滤波器剪枝方法分为"主动式"（利用数据集生成特征图以量化滤波器重要性）和"被动式"（通过滤波器逐项范数计算重要性，无需数据驱动）。在高剪枝比下（需从网络中剪除大量滤波器时），逐项范数方法会消除范数较小的滤波器，却未考虑这些滤波器在产生节点输出中的重要性，导致性能下降。为解决该问题，我们提出一种被动滤波器剪枝方法，通过考虑滤波器的算子范数，基于其对输出贡献值进行剪枝。与基于逐项范数的剪枝方法相比，所提方法在不同CNNs架构上具有更强的泛化能力。与现有主动滤波器剪枝方法相比，所提方法在计算滤波器重要性时速度提升至少4.5倍，且能达到与主动剪枝方法相近的性能。我们基于VGGish、DCASE21_Net、VGG-16和ResNet-50等多种CNNs架构，在音频场景分类和图像分类任务上评估了所提剪枝方法的有效性。