Deep convolutional neural networks are shown to be overkill with high parametric and computational redundancy in many application scenarios, and an increasing number of works have explored model pruning to obtain lightweight and efficient networks. However, most existing pruning approaches are driven by empirical heuristic and rarely consider the joint impact of channels, leading to unguaranteed and suboptimal performance. In this paper, we propose a novel channel pruning method via Class-Aware Trace Ratio Optimization (CATRO) to reduce the computational burden and accelerate the model inference. Utilizing class information from a few samples, CATRO measures the joint impact of multiple channels by feature space discriminations and consolidates the layer-wise impact of preserved channels. By formulating channel pruning as a submodular set function maximization problem, CATRO solves it efficiently via a two-stage greedy iterative optimization procedure. More importantly, we present theoretical justifications on convergence of CATRO and performance of pruned networks. Experimental results demonstrate that CATRO achieves higher accuracy with similar computation cost or lower computation cost with similar accuracy than other state-of-the-art channel pruning algorithms. In addition, because of its class-aware property, CATRO is suitable to prune efficient networks adaptively for various classification subtasks, enhancing handy deployment and usage of deep networks in real-world applications.

翻译：深度卷积神经网络在许多应用场景中被证明存在参数和计算冗余过高的问题，越来越多的研究通过模型剪枝来获得轻量高效的网络。然而，现有大多数剪枝方法依赖经验启发式策略，且很少考虑通道间的联合影响，导致性能无法保证且非最优。本文提出一种新颖的基于类别感知迹比优化（CATRO）的通道剪枝方法，旨在降低计算负担并加速模型推理。通过利用少量样本的类别信息，CATRO 借助特征空间判别性度量多个通道的联合影响，并整合保留通道的逐层影响。将通道剪枝建模为子模集函数最大化问题后，CATRO 通过两阶段贪心迭代优化过程高效求解。更重要的是，我们给出了 CATRO 收敛性及剪枝网络性能的理论证明。实验结果表明，与其他先进通道剪枝算法相比，CATRO 在相近计算成本下实现更高精度，或在相近精度下实现更低计算成本。此外，因其类别感知特性，CATRO 能够自适应地为各种分类子任务剪枝高效网络，从而促进深度网络在现实应用中的便捷部署与使用。