# Learning Filter Basis for Convolutional Neural Network Compression

Source: [Learning Filter Basis for Convolutional Neural Network Compression](<https://www.sota2.com/research/paper/68fa66d51e209131cea12c08>)

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

Data updated: 2025-10-25T22:00:21.133Z

Authors: Yawei Li, Shuhang Gu, Luc Van Gool, Radu Timofte

Published: 2019-08-23T17:55:26.000Z

## Abstract

Convolutional neural networks (CNNs) based solutions have achieved state-of-the-art performances for many computer vision tasks, including classification and super-resolution of images. Usually the success of these methods comes with a cost of millions of parameters due to stacking deep convolutional layers. Moreover, quite a large number of filters are also used for a single convolutional layer, which exaggerates the parameter burden of current methods. Thus, in this paper, we try to reduce the number of parameters of CNNs by learning a basis of the filters in convolutional layers. For the forward pass, the learned basis is used to approximate the original filters and then used as parameters for the convolutional layers. We validate our proposed solution for multiple CNN architectures on image classification and image super-resolution benchmarks and compare favorably to the existing state-of-the-art in terms of reduction of parameters and preservation of accuracy.

## 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/1908.08932>)

[PDF](<https://arxiv.org/pdf/1908.08932.pdf>)
