Liu Jingjing, Huang Lingjin, Feng Manlong, Guo Aiying, Yin Luqiao, Zhang Jianhua
Shanghai Key Laboratory of Chips and Systems for Intelligent Connected Vehicle, School of Microelectronics, Shanghai University, Shanghai 200444, China.
Sensors (Basel). 2025 Apr 3;25(7):2261. doi: 10.3390/s25072261.
Network pruning is a deep learning model compression technique aimed at reducing model storage requirements and decreasing computational resource consumption. However, mainstream pruning techniques often encounter challenges such as limited precision in feature selection and a diminished feature extraction capability. To address these issues, we propose an information extraction-based sparse stripe pruning (IESSP) method. This method introduces an information extraction module (IEM), which enhances stripe selection through a mask-based mechanism, promoting inter-layer interactions and directing the network's focus toward key features. In addition, we design a novel loss function that links output loss to stripe selection, enabling an effective balance between accuracy and efficiency. This loss function also supports the adaptive optimization of stripe sparsity during training. Experimental results on benchmark datasets demonstrate that the proposed method outperforms existing techniques. Specifically, when applied to prune the VGG-16 model on the CIFAR-10 dataset, the proposed method achieves a 0.29% improvement in accuracy while reducing FLOPs by 75.88% compared to the baseline.
网络剪枝是一种深度学习模型压缩技术，旨在降低模型存储需求并减少计算资源消耗。然而，主流剪枝技术常常面临诸如特征选择精度有限和特征提取能力下降等挑战。为了解决这些问题，我们提出了一种基于信息提取的稀疏条纹剪枝（IESSP）方法。该方法引入了一个信息提取模块（IEM），它通过基于掩码的机制增强条纹选择，促进层间交互并引导网络关注关键特征。此外，我们设计了一种新颖的损失函数，将输出损失与条纹选择联系起来，从而在准确性和效率之间实现有效平衡。该损失函数还支持在训练期间对条纹稀疏性进行自适应优化。在基准数据集上的实验结果表明，所提出的方法优于现有技术。具体而言，当应用于在CIFAR-10数据集上剪枝VGG-16模型时，与基线相比，所提出的方法在准确率上提高了0.29%，同时将浮点运算次数减少了75.88%。
