通过多维剪枝提升CNN在嵌入式设备上的效率
Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning
- 同时剪枝网络深度、宽度和分辨率三个维度
- 在多个基准上实现精度与效率的更好平衡
- 适合资源受限的嵌入式部署场景
本文提出TECO，一种多维剪枝框架，可协同剪枝卷积神经网络（CNN）的深度、宽度和分辨率三个维度，以提升在嵌入式硬件上的执行效率。TECO首先引入双阶段重要性评估机制，从局部和全局两个角度高效全面地评估每个剪枝单元的重要性。基于该评估框架，设计了一种启发式剪枝算法，逐步剪枝网络三个维度，以实现精度与效率之间的最优权衡。在多个基准测试中，TECO的表现优于现有最先进方法。代码和预训练模型已公开于https://github.com/ntuliuteam/Teco。
原文摘要 · Abstract (English)
In this paper, we propose TECO, a multi-dimensional pruning framework to collaboratively prune the three dimensions (depth, width, and resolution) of convolutional neural networks (CNNs) for better execution efficiency on embedded hardware. In TECO, we first introduce a two-stage importance evaluation framework, which efficiently and comprehensively evaluates each pruning unit according to both the local importance inside each dimension and the global importance across different dimensions. Based on the evaluation framework, we present a heuristic pruning algorithm to progressively prune the three dimensions of CNNs towards the optimal trade-off between accuracy and efficiency. Experiments on multiple benchmarks validate the advantages of TECO over existing state-of-the-art (SOTA) approaches. The code and pre-trained models are available at https://github.com/ntuliuteam/Teco.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。