cicNet: Improving the Efficiency of Convolutional Neural Network using Channel Local Convolutions
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)(2018)
摘要
Depthwise convolution and grouped convolution has been successfully applied to improve the efficiency of convolutional neural network (CNN). We suggest that these models can be considered as special cases of a generalized convolution operation, named channel local convolution(CLC), where an output channel is computed using a subset of the input channels. This definition entails computation dependency relations between input and output channels, which can be represented by a channel dependency graph(CDG). By modifying the CDG of grouped convolution, a new CLC kernel named interlaced grouped convolution (IGC) is created. Stacking IGC and GC kernels results in a convolution block (named CLC Block) for approximating regular convolution. By resorting to the CDG as an analysis tool, we derive the rule for setting the meta-parameters of IGC and GC and the framework for minimizing the computational cost. A new CNN model named cicNet is then constructed using CLC blocks, which shows significantly higher computational efficiency and fewer parameters compared to stateof-the-art networks, when being tested using the ImageNet-1K dataset.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络