CP-decomposition with Tensor Power Method for Convolutional Neural Networks Compression
(1701.07148)Abstract
Convolutional Neural Networks (CNNs) has shown a great success in many areas including complex image classification tasks. However, they need a lot of memory and computational cost, which hinders them from running in relatively low-end smart devices such as smart phones. We propose a CNN compression method based on CP-decomposition and Tensor Power Method. We also propose an iterative fine tuning, with which we fine-tune the whole network after decomposing each layer, but before decomposing the next layer. Significant reduction in memory and computation cost is achieved compared to state-of-the-art previous work with no more accuracy loss.
We're not able to analyze this paper right now due to high demand.
Please check back later (sorry!).
Generate a summary of this paper on our Pro plan:
We ran into a problem analyzing this paper.