Compressing complex convolutional neural network based on an improved deep compression algorithm
This work addresses the deployment challenge for Complex CNNs on mobile devices, representing an incremental extension of existing compression methods to a new domain.
The paper tackles the problem of compressing complex-valued convolutional neural networks (Complex CNNs) for deployment on embedded devices, achieving an 8x compression on CIFAR-10 with less than 3% accuracy loss and 16x compression on ImageNet with about 2% accuracy loss without retraining.
Although convolutional neural network (CNN) has made great progress, large redundant parameters restrict its deployment on embedded devices, especially mobile devices. The recent compression works are focused on real-value convolutional neural network (Real CNN), however, to our knowledge, there is no attempt for the compression of complex-value convolutional neural network (Complex CNN). Compared with the real-valued network, the complex-value neural network is easier to optimize, generalize, and has better learning potential. This paper extends the commonly used deep compression algorithm from real domain to complex domain and proposes an improved deep compression algorithm for the compression of Complex CNN. The proposed algorithm compresses the network about 8 times on CIFAR-10 dataset with less than 3% accuracy loss. On the ImageNet dataset, our method compresses the model about 16 times and the accuracy loss is about 2% without retraining.