201. Convolution with Logarithmic Filter Groups for Efficient Shallow CNN
- Author
-
Wissam J. Baddar, Tae Kwan Lee, Yong Man Ro, and Seong Tae Kim
- Subjects
Logarithm ,business.industry ,Computer science ,Computer Science::Neural and Evolutionary Computation ,Pattern recognition ,02 engineering and technology ,010501 environmental sciences ,Object (computer science) ,Network parameter ,01 natural sciences ,Convolutional neural network ,Convolution ,Nonlinear system ,Distribution (mathematics) ,Filter (video) ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,0105 earth and related environmental sciences - Abstract
In convolutional neural networks (CNNs), the filter grouping in convolution layers is known to be useful to reduce the network parameter size. In this paper, we propose a new logarithmic filter grouping which can capture the nonlinearity of filter distribution in CNNs. The proposed logarithmic filter grouping is installed in shallow CNNs applicable in a mobile application. Experiments were performed with the shallow CNNs for classification tasks. Our classification results on Multi-PIE dataset for facial expression recognition and CIFAR-10 dataset for object classification reveal that the compact CNN with the proposed logarithmic filter grouping scheme outperforms the same network with the uniform filter grouping in terms of accuracy and parameter efficiency. Our results indicate that the efficiency of shallow CNNs can be improved by the proposed logarithmic filter grouping.
- Published
- 2018