Frequency Domain Compact 3d Convolutional Neural Networks
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)(2020)
摘要
This paper studies the compression and acceleration of 3-dimensional convolutional neural networks (3D CNNs). To reduce the memory cost and computational complexity of deep neural networks, a number of algorithms have been explored by discovering redundant parameters in pre-trained networks. However, most of existing methods are designed for processing neural networks consisting of 2-dimensional convolution filters (i.e. image classification and detection) and cannot be straightforwardly applied for 3-dimensional filters (i.e. time series data). In this paper, we develop a novel approach for eliminating redundancy in the time dimensionality of 3D convolution filters by converting them into the frequency domain through a series of learned optimal transforms with extremely fewer parameters. Moreover, these transforms are forced to be orthogonal, and the calculation of feature maps can be accomplished in the frequency domain to achieve considerable speed-up rates. Experimental results on benchmark 3D CNN models and datasets demonstrate that the proposed Frequency Domain Compact 3D CNNs (FDC3D) can achieve the state-of-the-art performance, e.g. a 2 x speed-up ratio on the 3D-ResNet-18 without obviously affecting its accuracy.
更多查看译文
关键词
3D CNNs,deep neural networks,2-dimensional convolution filters,time dimensionality,3D convolution filters,FDC3D,3-dimensional convolutional neural networks,frequency domain compact 3D convolutional neural networks,memory cost,computational complexity,feature maps,computer vision
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络