FGP: Feature-Gradient-Prune for Efficient Convolutional Layer Pruning

TL;DR

FGP introduces a novel structured pruning method that combines feature and gradient information to more effectively remove redundant convolutional channels, leading to more efficient models with minimal accuracy loss.

Contribution

This paper presents the first feature-gradient integrated pruning technique that improves channel importance evaluation for better model compression.

Findings

Significantly reduces computational costs.

Maintains stable model performance.

Outperforms existing pruning methods in efficiency and accuracy.

Abstract

To reduce computational overhead while maintaining model performance, model pruning techniques have been proposed. Among these, structured pruning, which removes entire convolutional channels or layers, significantly enhances computational efficiency and is compatible with hardware acceleration. However, existing pruning methods that rely solely on image features or gradients often result in the retention of redundant channels, negatively impacting inference efficiency. To address this issue, this paper introduces a novel pruning method called Feature-Gradient Pruning (FGP). This approach integrates both feature-based and gradient-based information to more effectively evaluate the importance of channels across various target classes, enabling a more accurate identification of channels that are critical to model performance. Experimental results demonstrate that the proposed method improves both model compactness and practicality while maintaining stable performance. Experiments conducted across multiple tasks and datasets show that FGP significantly reduces computational costs and minimizes accuracy loss compared to existing methods, highlighting its effectiveness in optimizing pruning outcomes. The source code is available at: https://github.com/FGP-code/FGP.