# CNNPruner: Pruning Convolutional Neural Networks with Visual Analytics

arXiv: https://arxiv.org/abs/2009.09940 · HTML: https://mlsanity.com/paper/2009.09940/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2020.

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

- [Visual Analytics For Machine Learning: A Data Perspective Survey](https://mlsanity.com/paper/2307.07712/) (2023)
- [NeuroCartography: Scalable Automatic Visual Summarization of Concepts in Deep Neural Networks](https://mlsanity.com/paper/2108.12931/) (2021)
- [Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference](https://mlsanity.com/paper/2404.03085/) (2024)
- [Compress and Compare: Interactively Evaluating Efficiency and Behavior Across ML Model Compression Experiments](https://mlsanity.com/paper/2408.03274/) (2024)
- [Illuminating LLM Coding Agents: Visual Analytics for Deeper Understanding and Enhancement](https://mlsanity.com/paper/2508.12555/) (2025)
- [Evaluation of Explanation Methods of AI -- CNNs in Image Classification Tasks with Reference-based and No-reference Metrics](https://mlsanity.com/paper/2212.01222/) (2022)
- [ViNNPruner: Visual Interactive Pruning for Deep Learning](https://mlsanity.com/paper/2205.15731/) (2022)
- ["Understanding Robustness Lottery": A Geometric Visual Comparative Analysis of Neural Network Pruning Approaches](https://mlsanity.com/paper/2206.07918/) (2022)
- [A Novel Correlation-optimized Deep Learning Method for Wind Speed Forecast](https://mlsanity.com/paper/2306.01986/) (2023)
- [SPLite Hand: Sparsity-Aware Lightweight 3D Hand Pose Estimation](https://mlsanity.com/paper/2510.16396/) (2025)
- [Token Signatures of Code: Comparing Coding Behaviors Across Large Language Models](https://mlsanity.com/paper/2609.22097/) (2026)

## Abstract (arXiv)

Convolutional neural networks (CNNs) have demonstrated extraordinarily good performance in many computer vision tasks. The increasing size of CNN models, however, prevents them from being widely deployed to devices with limited computational resources, e.g., mobile/embedded devices. The emerging topic of model pruning strives to address this problem by removing less important neurons and fine-tuning the pruned networks to minimize the accuracy loss. Nevertheless, existing automated pruning solutions often rely on a numerical threshold of the pruning criteria, lacking the flexibility to optimally balance the trade-off between model size and accuracy. Moreover, the complicated interplay between the stages of neuron pruning and model fine-tuning makes this process opaque, and therefore becomes difficult to optimize. In this paper, we address these challenges through a visual analytics approach, named CNNPruner. It considers the importance of convolutional filters through both instability and sensitivity, and allows users to interactively create pruning plans according to a desired goal on model size or accuracy. Also, CNNPruner integrates state-of-the-art filter visualization techniques to help users understand the roles that different filters played and refine their pruning plans. Through comprehensive case studies on CNNs with real-world sizes, we validate the effectiveness of CNNPruner.