Convolutional neural networks have demonstrated impressive results in many computer vision tasks. However, the increasing size of these networks raises concerns about the information overload resulting from the large number of network parameters. In this paper, we propose Frequency Regularization to restrict the non-zero elements of the network parameters in the frequency domain. The proposed approach operates at the tensor level, and can be applied to almost all network architectures. Specifically, the tensors of parameters are maintained in the frequency domain, where high frequency components can be eliminated by zigzag setting tensor elements to zero. Then, the inverse discrete cosine transform (IDCT) is used to reconstruct the spatial tensors for matrix operations during network training. Since high frequency components of images are known to be less critical, a large proportion of these parameters can be set to zero when networks are trained with the proposed frequency regularization. Comprehensive evaluations on various state-of-the-art network architectures, including LeNet, Alexnet, VGG, Resnet, ViT, UNet, GAN, and VAE, demonstrate the effectiveness of the proposed frequency regularization. For a very small accuracy decrease (less than 2\%), a LeNet5 with 0.4M parameters can be represented by only 776 float16 numbers (over 1100$\times$ reduction), and a UNet with 34M parameters can be represented by only 759 float16 numbers (over 80000$\times$ reduction). In particular, the original size of the UNet model is 366MB, we reduce it to 4.5kb.
翻译:卷积神经网络已经在许多计算机视觉任务中展现出了出色的结果。然而,这些网络的不断扩大引起了有关大量网络参数导致信息过载的担忧。本文提出了一种频率正则化的方法,在频域中限制网络参数的非零元素。所提出的方法在张量级别上操作,适用于几乎所有的网络架构。具体来说,参数的张量在频域中维护,可以通过将高频组件的张量元素设置为零来消除这些组件。然后,在网络训练期间使用反离散余弦变换(IDCT)将空间张量重构为矩阵运算。由于认为图像的高频组件不太重要,因此在使用所提出的频率正则化进行网络训练时,大部分这些参数可以设置为零。对各种最先进的网络架构进行了全面评估,包括LeNet,AlexNet,VGG,ResNet,ViT,UNet,GAN和VAE,证明了所提出的频率正则化的有效性。对于很小的精度损失(小于2%),具有0.4M参数的LeNet5仅可以用776个float16数字表示(超过1100倍的减少),具有34M参数的UNet仅可以用759个float16数字表示(超过80000倍的减少)。特别是,UNet模型的原始大小为366MB,我们将其缩减为4.5kb。