SCSP: Spectral Clustering Filter Pruning with Soft Self-adaption Manners
SCSP: Spectral Clustering Filter Pruning with Soft Self-adaption Manners
复制标题
DOI：
--
复制
发表时间：
2018-06
期刊：
影响因子：
--
通讯作者：
Huiyuan Zhuo;Xuelin Qian;Yanwei Fu;Heng Yang;X. Xue
中科院分区：
文献类型：
--
作者：
Huiyuan Zhuo;Xuelin Qian;Yanwei Fu;Heng Yang;X. Xue
深度卷积神经网络（CNN）在计算机视觉领域取得了巨大的成功。然而，深度复杂模型的高计算成本阻碍了在具有有限内存和计算资源的边缘设备上的部署。本文提出了一种新的卷积神经网络压缩滤波器剪枝方法，即谱聚类软自适应滤波器剪枝（SCSP）。我们首先逐层对过滤器应用谱聚类，以探索它们的内在联系，并只依赖于有效的组。通过自适应的方式，可以在较少的时期内完成剪枝操作，使网络逐渐选择有意义的组。根据这种策略，我们不仅实现了模型压缩，同时保持相当的性能，而且找到了一个新的角度来解释模型压缩过程。
Deep Convolutional Neural Networks (CNN) has achieved significant success in computer vision field. However, the high computational cost of the deep complex models prevents the deployment on edge devices with limited memory and computational resource. In this paper, we proposed a novel filter pruning for convolutional neural networks compression, namely spectral clustering filter pruning with soft self-adaption manners (SCSP). We first apply spectral clustering on filters layer by layer to explore their intrinsic connections and only count on efficient groups. By self-adaption manners, the pruning operations can be done in few epochs to let the network gradually choose meaningful groups. According to this strategy, we not only achieve model compression while keeping considerable performance, but also find a novel angle to interpret the model compression process.