Convolution with Logarithmic Filter Groups for Efficient Shallow CNN
This work addresses efficiency improvements for shallow CNNs in mobile applications, but it is incremental as it builds on existing filter grouping techniques.
The paper tackles the problem of reducing parameter size in convolutional neural networks (CNNs) by proposing a logarithmic filter grouping scheme for shallow CNNs, achieving improved accuracy and parameter efficiency on Multi-PIE and CIFAR-10 datasets compared to uniform grouping.
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.