The advancement of convolutional neural networks (CNNs) on various vision applications has attracted lots of attention. Yet the majority of CNNs are unable to satisfy the strict requirement for real-world deployment. To overcome this, the recent popular network pruning is an effective method to reduce the redundancy of the models. However, the ranking of filters according to their "importance" on different pruning criteria may be inconsistent. One filter could be important according to a certain criterion, while it is unnecessary according to another one, which indicates that each criterion is only a partial view of the comprehensive "importance". From this motivation, we propose a novel framework to integrate the existing filter pruning criteria by exploring the criteria diversity. The proposed framework contains two stages: Criteria Clustering and Filters Importance Calibration. First, we condense the pruning criteria via layerwise clustering based on the rank of "importance" score. Second, within each cluster, we propose a calibration factor to adjust their significance for each selected blending candidates and search for the optimal blending criterion via Evolutionary Algorithm. Quantitative results on the CIFAR-100 and ImageNet benchmarks show that our framework outperforms the state-of-the-art baselines, regrading to the compact model performance after pruning.
翻译:在各种视觉应用中,共进神经网络的进步引起了许多关注。 然而,大多数CNN无法满足真实世界部署的严格要求。 要克服这一点,最近流行网络的运行是减少模型冗余的有效方法。 但是,过滤器的“重要性”在不同的修剪标准上可能不一致。 一种过滤器根据某一标准可能很重要, 而另一种标准则没有必要, 表明每个标准只是全面“ 重要性” 的局部视图。 我们从这个动机出发, 提出了一个新框架, 通过探索标准的多样性, 整合现有的过滤器运行标准。 拟议的框架包含两个阶段: 标准分组和过滤器重要性校准。 首先, 我们根据“ 进口” 评分, 通过分分的层化组合来压缩标定标准。 第二, 在每一组中, 我们提出一个校准系数, 以调整每个选定的混合候选人的重要性, 并通过进化Algorithm 搜索最佳混合标准。 我们的CIFAR- 100 的定量模型和图像网络运行基准显示我们的升级基准。