通过跳层与频率调节，实现低延迟下的高效低耗推理。
Optimization of Layer Skipping and Frequency Scaling for Convolutional Neural Networks under Latency Constraint
- 采用比例跳层和频率调节协同优化计算与能耗。
- ResNet-152在CIFAR-10上能耗降低显著，精度损失极小。
- 适合移动端、自动驾驶等资源受限场景部署。
卷积神经网络（CNN）的能耗是部署深度学习模型于移动设备、自动驾驶车辆等资源受限设备时的关键挑战。本文提出一种结合比例跳层（PLS）与频率调节（FS）的方法：跳层通过选择性跳过网络层降低计算复杂度，频率调节则动态调整处理器频率以在延迟约束下优化能效。在ResNet-152与CIFAR-10数据集上的实验表明，该方法显著降低了计算需求与能耗，同时保持了极小的精度损失。研究为资源受限环境下的实时处理提供了实用方案，并揭示了计算效率与模型性能间的平衡机制。
原文摘要 · Abstract (English)
The energy consumption of Convolutional Neural Networks (CNNs) is a critical factor in deploying deep learning models on resource-limited equipment such as mobile devices and autonomous vehicles. We propose an approach involving Proportional Layer Skipping (PLS) and Frequency Scaling (FS). Layer skipping reduces computational complexity by selectively bypassing network layers, whereas frequency scaling adjusts the frequency of the processor to optimize energy use under latency constraints. Experiments of PLS and FS on ResNet-152 with the CIFAR-10 dataset demonstrated significant reductions in computational demands and energy consumption with minimal accuracy loss. This study offers practical solutions for improving real-time processing in resource-limited settings and provides insights into balancing computational efficiency and model performance.
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。