# Optimization of Layer Skipping and Frequency Scaling for Convolutional Neural Networks under Latency Constraint

arXiv: https://arxiv.org/abs/2503.24014 · HTML: https://mlsanity.com/paper/2503.24014/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 31 Mar 2025.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [Conditional Computation in Neural Networks for faster models](https://mlsanity.com/paper/1511.06297/) (2015)
- [Spatially Adaptive Computation Time for Residual Networks](https://mlsanity.com/paper/1612.02297/) (2016)
- [Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges](https://mlsanity.com/paper/2103.04505/) (2021)
- [Training Quantized Nets: A Deeper Understanding](https://mlsanity.com/paper/1706.02379/) (2017)
- [Training CNNs with Low-Rank Filters for Efficient Image Classification](https://mlsanity.com/paper/1511.06744/) (2015)
- [Model Compression in Practice: Lessons Learned from Practitioners Creating On-device Machine Learning Experiences](https://mlsanity.com/paper/2310.04621/) (2023)
- [E2CM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning](https://mlsanity.com/paper/2103.01148/) (2021)
- [Online V2X Scheduling for Raw-Level Cooperative Perception](https://mlsanity.com/paper/2202.06085/) (2022)

## Abstract (arXiv)

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.