Compression of Deep Convolutional Neural Networks under Joint Sparsity Constraints

Understand

We consider the optimization of deep convolutional neural networks (CNNs) such that they provide good performance while having reduced complexity if deployed on either conventional systems utilizing spatial-domain convolution or lower complexity systems designed for Winograd convolution.

• Furthermore, we explore the universal quantization and compression of these networks.
• In particular, the proposed framework produces one compressed model whose convolutional filters can be made sparse either in the spatial domain or in the Winograd domain.
• Hence, one compressed model can be deployed universally on any platform, without need for re-training on the deployed platform, and the sparsity of its convolutional filters can be exploited for further complexity reduction in either domain.