# Iterative Filter Pruning for Concatenation-based CNN Architectures

arXiv: https://arxiv.org/abs/2405.03715 · HTML: https://mlsanity.com/paper/2405.03715/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 33 references that are in the map.
- First posted on arXiv 4 May 2024.

## Builds on (most cited first, 24 of 24)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [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)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [EIE: Efficient Inference Engine on Compressed Deep Neural Network](https://mlsanity.com/paper/1602.01528/) (2016)
- [Comparing Rewinding and Fine-tuning in Neural Network Pruning](https://mlsanity.com/paper/2003.02389/) (2020)
- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [Vision Meets Drones: A Challenge](https://mlsanity.com/paper/1804.07437/) (2018)
- [Gemmini: Enabling Systematic Deep-Learning Architecture Evaluation via Full-Stack Integration](https://mlsanity.com/paper/1911.09925/) (2019)
- [Designing Network Design Strategies Through Gradient Path Analysis](https://mlsanity.com/paper/2211.04800/) (2022)
- [Network Pruning That Matters: A Case Study on Retraining Variants](https://mlsanity.com/paper/2105.03193/) (2021)
- [SlimYOLOv3: Narrower, Faster and Better for Real-Time UAV Applications](https://mlsanity.com/paper/1907.11093/) (2019)
- [Relationship between Model Compression and Adversarial Robustness: A Review of Current Evidence](https://mlsanity.com/paper/2311.15782/) (2023)
- [Channel Pruned YOLOv5-based Deep Learning Approach for Rapid and Accurate Outdoor Obstacles Detection](https://mlsanity.com/paper/2204.13699/) (2022)
- [Integration of a systolic array based hardware accelerator into a DNN operator auto-tuning framework](https://mlsanity.com/paper/2212.03034/) (2022)
- [Model Compression Methods for YOLOv5: A Review](https://mlsanity.com/paper/2307.11904/) (2023)

## Built on by (most cited first, 4 of 4)

- [FastFLUX: Pruning FLUX with Block-wise Replacement and Sandwich Training](https://mlsanity.com/paper/2506.10035/) (2025)
- [Enhanced Pruning Strategy for Multi-Component Neural Architectures Using Component-Aware Graph Analysis](https://mlsanity.com/paper/2504.13296/) (2025)
- [Efficient Edge AI: Deploying Convolutional Neural Networks on FPGA with the Gemmini Accelerator](https://mlsanity.com/paper/2408.07404/) (2024)
- [COMponent-Aware Pruning for Accelerated Control Tasks in Latent Space Models](https://mlsanity.com/paper/2508.08144/) (2025)

## Abstract (arXiv)

Model compression and hardware acceleration are essential for the resource-efficient deployment of deep neural networks. Modern object detectors have highly interconnected convolutional layers with concatenations. In this work, we study how pruning can be applied to such architectures, exemplary for YOLOv7. We propose a method to handle concatenation layers, based on the connectivity graph of convolutional layers. By automating iterative sensitivity analysis, pruning, and subsequent model fine-tuning, we can significantly reduce model size both in terms of the number of parameters and FLOPs, while keeping comparable model accuracy. Finally, we deploy pruned models to FPGA and NVIDIA Jetson Xavier AGX. Pruned models demonstrate a 2x speedup for the convolutional layers in comparison to the unpruned counterparts and reach real-time capability with 14 FPS on FPGA. Our code is available at https://github.com/fzi-forschungszentrum-informatik/iterative-yolo-pruning.