# CP-decomposition with Tensor Power Method for Convolutional Neural Networks Compression

Source: [CP-decomposition with Tensor Power Method for Convolutional Neural Networks Compression](<https://www.sota2.com/research/paper/68fa63171e209131ce9fc991>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:32:19.733Z

Authors: Marcella Astrid, Seung-Ik Lee

Published: 2017-01-25T02:58:06.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1701.07148>)

[PDF](<https://arxiv.org/pdf/1701.07148.pdf>)