SeKron：一种支持多种分解结构的分解方法
SeKron: A Decomposition Method Supporting Many Factorization Structures
摘要：
虽然卷积神经网络（CNN）已经成为大多数图像处理和计算机视觉应用的事实标准，但它们在边缘设备上的部署仍然具有挑战性。张量分解方法提供了一种压缩CNN的方法，通过对其卷积张量施加某些因子分解结构来满足广泛的设备约束。然而，受限于由最先进的分解方法呈现的小的因子分解结构集合可能导致次优性能。我们提出SeKron，一种新的张量分解方法，提供了各种各样的分解结构，使用序列的克罗内克产品。通过递归地找到近似的克罗内克因子，我们到达每个分解结构的最佳分解。我们表明，SeKron是一个灵活的分解，推广了广泛使用的方法，如张量列车（TT），张量环（TR），规范多矢（CP）和塔克分解。至关重要的是，我们得到了一个有效的卷积投影算法共享的所有SeKron结构，导致无缝压缩的CNN模型。我们在高级和低级计算机视觉任务上验证了SeKron的模型压缩，并发现它优于最先进的分解方法。
英文摘要：
While convolutional neural networks (CNNs) have become the de facto standard for most image processing and computer vision applications, their deployment on edge devices remains challenging. Tensor decomposition methods provide a means of compressing CNNs to meet the wide range of device constraints by imposing certain factorization structures on their convolution tensors. However, being limited to the small set of factorization structures presented by state-of-the-art decomposition approaches can lead to sub-optimal performance. We propose SeKron, a novel tensor decomposition method that offers a wide variety of factorization structures, using sequences of Kronecker products. By recursively finding approximating Kronecker factors, we arrive at optimal decompositions for each of the factorization structures. We show that SeKron is a flexible decomposition that generalizes widely used methods, such as Tensor-Train (TT), Tensor-Ring (TR), Canonical Polyadic (CP) and Tucker decompositions. Crucially, we derive an efficient convolution projection algorithm shared by all SeKron structures, leading to seamless compression of CNN models. We validate SeKron for model compression on both high-level and low-level computer vision tasks and find that it outperforms state-of-the-art decomposition methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
