# Exploring Gradient Flow Based Saliency for DNN Model Compression

Source: [Exploring Gradient Flow Based Saliency for DNN Model Compression](<https://www.sota2.com/research/paper/68fa6b1a1e209131cea2c381>)

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

Data updated: 2025-10-25T23:40:16.064Z

Authors: Xinyu Liu, Baopu Li, Zhen Chen, Yixuan Yuan

Published: 2021-10-24T16:09:40.000Z

## Abstract

Model pruning aims to reduce the deep neural network (DNN) model size or computational overhead. Traditional model pruning methods such as l-1 pruning that evaluates the channel significance for DNN pay too much attention to the local analysis of each channel and make use of the magnitude of the entire feature while ignoring its relevance to the batch normalization (BN) and ReLU layer after each convolutional operation. To overcome these problems, we propose a new model pruning method from a new perspective of gradient flow in this paper. Specifically, we first theoretically analyze the channel's influence based on Taylor expansion by integrating the effects of BN layer and ReLU activation function. Then, the incorporation of the first-order Talyor polynomial of the scaling parameter and the shifting parameter in the BN layer is suggested to effectively indicate the significance of a channel in a DNN. Comprehensive experiments on both image classification and image denoising tasks demonstrate the superiority of the proposed novel theory and scheme. Code is available at https://github.com/CityU-AIM-Group/GFBS.

## 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/2110.12477>)

[PDF](<https://arxiv.org/pdf/2110.12477.pdf>)
