# Complexity-Driven CNN Compression for Resource-constrained Edge AI

arXiv: https://arxiv.org/abs/2208.12816 · HTML: https://mlsanity.com/paper/2208.12816/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 54 references that are in the map.
- First posted on arXiv 26 Aug 2022.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Linear Mode Connectivity and the Lottery Ticket Hypothesis](https://mlsanity.com/paper/1912.05671/) (2019)
- [Rethinking the Value of Network Pruning](https://mlsanity.com/paper/1810.05270/) (2018)
- [Carbon Emissions and Large Neural Network Training](https://mlsanity.com/paper/2104.10350/) (2021)
- [Pruning neural networks without any data by iteratively conserving synaptic flow](https://mlsanity.com/paper/2006.05467/) (2020)
- [The State of Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1902.09574/) (2019)
- [Picking Winning Tickets Before Training by Preserving Gradient Flow](https://mlsanity.com/paper/2002.07376/) (2020)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [Dynamic Network Surgery for Efficient DNNs](https://mlsanity.com/paper/1608.04493/) (2016)
- [Pruning Neural Networks at Initialization: Why are We Missing the Mark?](https://mlsanity.com/paper/2009.08576/) (2020)
- [Discrimination-aware Channel Pruning for Deep Neural Networks](https://mlsanity.com/paper/1810.11809/) (2018)
- [Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing](https://mlsanity.com/paper/1910.05316/) (2019)
- [Towards Optimal Structured CNN Pruning via Generative Adversarial Learning](https://mlsanity.com/paper/1903.09291/) (2019)
- [An Entropy-based Pruning Method for CNN Compression](https://mlsanity.com/paper/1706.05791/) (2017)
- [Non-Structured DNN Weight Pruning -- Is It Beneficial in Any Platform?](https://mlsanity.com/paper/1907.02124/) (2019)
- [Training Your Sparse Neural Network Better with Any Mask](https://mlsanity.com/paper/2206.12755/) (2022)
- [PCNN: Pattern-based Fine-Grained Regular Pruning towards Optimizing CNN Accelerators](https://mlsanity.com/paper/2002.04997/) (2020)
- [Dynamic ConvNets on Tiny Devices via Nested Sparsity](https://mlsanity.com/paper/2203.03324/) (2022)
- [PCAS: Pruning Channels with Attention Statistics for Deep Network Compression](https://mlsanity.com/paper/1806.05382/) (2018)
- [Attention Based Pruning for Shift Networks](https://mlsanity.com/paper/1905.12300/) (2019)
- [Studying the Plasticity in Deep Convolutional Neural Networks using Random Pruning](https://mlsanity.com/paper/1812.10240/) (2018)

## Built on by (most cited first, 8 of 8)

- [Benchmarking Ultra-Low-Power μNPUs](https://mlsanity.com/paper/2503.22567/) (2025)
- [Improve Knowledge Distillation via Label Revision and Data Selection](https://mlsanity.com/paper/2404.03693/) (2024)
- [Deep Learning-based Techniques for Integrated Sensing and Communication Systems: State-of-the-Art, Challenges, and Opportunities](https://mlsanity.com/paper/2509.06968/) (2025)
- [Electrostatic Force Regularization for Neural Structured Pruning](https://mlsanity.com/paper/2411.11079/) (2024)
- [Energy-Efficient Uncertainty-Aware Biomass Composition Prediction at the Edge](https://mlsanity.com/paper/2404.11230/) (2024)
- [Deep Convolutional Neural Networks Structured Pruning via Gravity Regularization](https://mlsanity.com/paper/2411.16901/) (2024)
- [OptiFLIDS: Optimized Federated Learning for Energy-Efficient Intrusion Detection in IoT](https://mlsanity.com/paper/2510.05180/) (2025)
- [UtVAA: Ultra-tiny Vision Transformer with Affix Attention for Mobile Image Classification](https://mlsanity.com/paper/2606.14735/) (2026)

## Abstract (arXiv)

Recent advances in Artificial Intelligence (AI) on the Internet of Things (IoT)-enabled network edge has realized edge intelligence in several applications such as smart agriculture, smart hospitals, and smart factories by enabling low-latency and computational efficiency. However, deploying state-of-the-art Convolutional Neural Networks (CNNs) such as VGG-16 and ResNets on resource-constrained edge devices is practically infeasible due to their large number of parameters and floating-point operations (FLOPs). Thus, the concept of network pruning as a type of model compression is gaining attention for accelerating CNNs on low-power devices. State-of-the-art pruning approaches, either structured or unstructured do not consider the different underlying nature of complexities being exhibited by convolutional layers and follow a training-pruning-retraining pipeline, which results in additional computational overhead. In this work, we propose a novel and computationally efficient pruning pipeline by exploiting the inherent layer-level complexities of CNNs. Unlike typical methods, our proposed complexity-driven algorithm selects a particular layer for filter-pruning based on its contribution to overall network complexity. We follow a procedure that directly trains the pruned model and avoids the computationally complex ranking and fine-tuning steps. Moreover, we define three modes of pruning, namely parameter-aware (PA), FLOPs-aware (FA), and memory-aware (MA), to introduce versatile compression of CNNs. Our results show the competitive performance of our approach in terms of accuracy and acceleration. Lastly, we present a trade-off between different resources and accuracy which can be helpful for developers in making the right decisions in resource-constrained IoT environments.