Deep convolutional neural networks (CNNs) with a large number of parameters require intensive computational resources, and thus are hard to be deployed in resource-constrained platforms. Decomposition-based methods, therefore, have been utilized to compress CNNs in recent years. However, since the compression factor and performance are negatively correlated, the state-of-the-art works either suffer from severe performance degradation or have relatively low compression factors. To overcome this problem, we propose to compress CNNs and alleviate performance degradation via joint matrix decomposition, which is different from existing works that compressed layers separately. The idea is inspired by the fact that there are lots of repeated modules in CNNs. By projecting weights with the same structures into the same subspace, networks can be jointly compressed with larger ranks. In particular, three joint matrix decomposition schemes are developed, and the corresponding optimization approaches based on Singular Value Decomposition are proposed. Extensive experiments are conducted across three challenging compact CNNs for different benchmark data sets to demonstrate the superior performance of our proposed algorithms. As a result, our methods can compress the size of ResNet-34 by 22X with slighter accuracy degradation compared with several state-of-the-art methods.
翻译:具有大量参数的深相神经网络(CNN)需要大量计算资源,因此很难在资源限制的平台上部署。因此,近年来采用了基于分解的方法压缩CNN。然而,由于压缩系数和性能呈负相关关系,最先进的工程要么出现严重性能退化,要么存在相对较低的压缩因素。为了克服这一问题,我们提议通过联合矩阵分解压缩CNN,减轻性能退化,这与现有的压缩层不同。这种想法源于有线电视新闻网中存在许多重复模块这一事实。通过在同一次空间中投射同一结构的重量,网络可以与较大级别联合压缩。特别是,制定了三个联合矩阵分解计划,并提出了基于星值分解定位的相应优化办法。我们建议通过三个具有挑战性的小型CNNCM,对不同的基准数据集进行广泛的实验,以显示我们提议的算法的优异性。因此,我们的方法可以将ResNet-34的大小与22x的微精确度降解,与几种状态相比较。