# Cluster Pruning: An Efficient Filter Pruning Method for Edge AI Vision Applications

arXiv: https://arxiv.org/abs/2003.02449 · HTML: https://mlsanity.com/paper/2003.02449/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Mar 2020.

## Built on by (most cited first, 11 of 11)

- [Dynamic ConvNets on Tiny Devices via Nested Sparsity](https://mlsanity.com/paper/2203.03324/) (2022)
- [Pruning for Feature-Preserving Circuits in CNNs](https://mlsanity.com/paper/2206.01627/) (2022)
- [Latency-Memory Optimized Splitting of Convolution Neural Networks for Resource Constrained Edge Devices](https://mlsanity.com/paper/2107.09123/) (2021)
- [Intelligent Traffic Monitoring with Hybrid AI](https://mlsanity.com/paper/2209.00448/) (2022)
- [UniLCD: Unified Local-Cloud Decision-Making via Reinforcement Learning](https://mlsanity.com/paper/2409.11403/) (2024)
- [Pruning-Based TinyML Optimization of Machine Learning Models for Anomaly Detection in Electric Vehicle Charging Infrastructure](https://mlsanity.com/paper/2503.14799/) (2025)
- [WiFi Fingerprint Clustering for Urban Mobility Analysis](https://mlsanity.com/paper/2105.01274/) (2021)
- [A Real-time Low-cost Artificial Intelligence System for Autonomous Spraying in Palm Plantations](https://mlsanity.com/paper/2103.04132/) (2021)
- [SmartSplit: Latency-Energy-Memory Optimisation for CNN Splitting on Smartphone Environment](https://mlsanity.com/paper/2111.01077/) (2021)
- [Real-Time AI-Driven People Tracking and Counting Using Overhead Cameras](https://mlsanity.com/paper/2411.10072/) (2024)
- [Resource-Efficient Pruning for Transformer via Low-Rank Importance Estimation](https://mlsanity.com/paper/2608.24973/) (2026)

## Abstract (arXiv)

Even though the Convolutional Neural Networks (CNN) has shown superior results in the field of computer vision, it is still a challenging task to implement computer vision algorithms in real-time at the edge, especially using a low-cost IoT device due to high memory consumption and computation complexities in a CNN. Network compression methodologies such as weight pruning, filter pruning, and quantization are used to overcome the above mentioned problem. Even though filter pruning methodology has shown better performances compared to other techniques, irregularity of the number of filters pruned across different layers of a CNN might not comply with majority of the neural computing hardware architectures. In this paper, a novel greedy approach called cluster pruning has been proposed, which provides a structured way of removing filters in a CNN by considering the importance of filters and the underlying hardware architecture. The proposed methodology is compared with the conventional filter pruning algorithm on Pascal-VOC open dataset, and Head-Counting dataset, which is our own dataset developed to detect and count people entering a room. We benchmark our proposed method on three hardware architectures, namely CPU, GPU, and Intel Movidius Neural Computer Stick (NCS) using the popular SSD-MobileNet and SSD-SqueezeNet neural network architectures used for edge-AI vision applications. Results demonstrate that our method outperforms the conventional filter pruning methodology, using both datasets on above mentioned hardware architectures. Furthermore, a low cost IoT hardware setup consisting of an Intel Movidius-NCS is proposed to deploy an edge-AI application using our proposed pruning methodology.