Optimization of Layer Skipping and Frequency Scaling for Convolutional Neural Networks under Latency Constraint
This provides practical solutions for improving real-time processing in resource-limited settings like mobile devices and autonomous vehicles, but it is incremental as it builds on existing layer skipping and frequency scaling techniques.
The paper tackled the problem of high energy consumption in CNNs on resource-limited devices by proposing Proportional Layer Skipping and Frequency Scaling, resulting in significant reductions in computational demands and energy consumption with minimal accuracy loss on ResNet-152 with CIFAR-10.
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.