论文标题
WSEBP：用于多层卷积稀疏编码的新型宽度深度同步扩展算法
WSEBP: A Novel Width-depth Synchronous Extension-based Basis Pursuit Algorithm for Multi-Layer Convolutional Sparse Coding
论文作者
论文摘要
集成在多层卷积稀疏编码（ML-CSC）中的追求算法可以解释卷积神经网络（CNN）。但是，许多当前的最新（SOTA）追求算法需要多次迭代才能优化ML-CSC的解决方案，ML-CSC的解决方案将其应用程序限制为更深的CNN，这是由于高度计算成本和大量资源，以获得非常小的性能增长。在这项研究中，我们通过引入每一层有效的初始化策略来重点关注追求算法的0次迭代，通过该策略可以改善ML-CSC的解决方案。具体而言，我们首先提出了一种新型的宽度深度同步扩展基础追求（WSEBP）算法，该算法解决了ML-CSC问题，而无需与SOTA算法相比，不限制迭代次数，并通过每层有效的初始化来最大化性能。然后，我们提出了一个简单而统一的基于ML-CSC的分类网络（ML-CSC-NET），该网络由基于ML-CSC的特征编码器和一个完全连接的层组成，以验证WSEBP在图像分类任务中的性能。实验结果表明，我们提出的WSEBP在准确性和消费资源方面优于SOTA算法。此外，在CNN中集成的WSEBP可以提高更深的CNN的性能，并使它们可解释。最后，以VGG为例，我们建议WSEBP-VGG13提高VGG13的性能，VGG13的性能在四个公共数据集上取得了竞争成果，即87.79％在CIFAR-10数据集中获得86.83％，而CIFAR-10数据集中的竞争结果为86.83％，58.01％vs. 54.60％vs. 54.60％cov in Cov 54.52.52％v.52％，91.52％，91.52％，91.52％，91.52％，91.52％。数据集分别为99.88％和99.78％的破解数据集。结果表明，提出的WSEBP的有效性，通过WSEBP改善了ML-CSC的性能以及对CNN或更深CNN的解释。
The pursuit algorithms integrated in multi-layer convolutional sparse coding (ML-CSC) can interpret the convolutional neural networks (CNNs). However, many current state-of-art (SOTA) pursuit algorithms require multiple iterations to optimize the solution of ML-CSC, which limits their applications to deeper CNNs due to high computational cost and large number of resources for getting very tiny gain of performance. In this study, we focus on the 0th iteration in pursuit algorithm by introducing an effective initialization strategy for each layer, by which the solution for ML-CSC can be improved. Specifically, we first propose a novel width-depth synchronous extension-based basis pursuit (WSEBP) algorithm which solves the ML-CSC problem without the limitation of the number of iterations compared to the SOTA algorithms and maximizes the performance by an effective initialization in each layer. Then, we propose a simple and unified ML-CSC-based classification network (ML-CSC-Net) which consists of an ML-CSC-based feature encoder and a fully-connected layer to validate the performance of WSEBP on image classification task. The experimental results show that our proposed WSEBP outperforms SOTA algorithms in terms of accuracy and consumption resources. In addition, the WSEBP integrated in CNNs can improve the performance of deeper CNNs and make them interpretable. Finally, taking VGG as an example, we propose WSEBP-VGG13 to enhance the performance of VGG13, which achieves competitive results on four public datasets, i.e., 87.79% vs. 86.83% on Cifar-10 dataset, 58.01% vs. 54.60% on Cifar-100 dataset, 91.52% vs. 89.58% on COVID-19 dataset, and 99.88% vs. 99.78% on Crack dataset, respectively. The results show the effectiveness of the proposed WSEBP, the improved performance of ML-CSC with WSEBP, and interpretation of the CNNs or deeper CNNs.
