mlsanityData to 14 Oct 2026

Iterative Filter Pruning for Concatenation-based CNN Architectures

arXiv 2405.03715 ↗First posted 4 May 2024cs.CVcited by 4

Not on the map. Why?

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.

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

24 of 33 references.

References · 24

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2018YOLOv3: An Incremental Improvementcited by 2,659
  5. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  6. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  7. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  8. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  9. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  10. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  11. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
  12. 2016Learning Structured Sparsity in Deep Neural Networkscited by 541
12 more
  1. 2016EIE: Efficient Inference Engine on Compressed Deep Neural Networkcited by 295
  2. 2020Comparing Rewinding and Fine-tuning in Neural Network Pruningcited by 240
  3. 2023DepGraph: Towards Any Structural Pruningcited by 203
  4. 2018Vision Meets Drones: A Challengecited by 81
  5. 2019Gemmini: Enabling Systematic Deep-Learning Architecture Evaluation via Full-Stack Integrationcited by 63
  6. 2022Designing Network Design Strategies Through Gradient Path Analysiscited by 32
  7. 2021Network Pruning That Matters: A Case Study on Retraining Variantscited by 25
  8. 2019SlimYOLOv3: Narrower, Faster and Better for Real-Time UAV Applicationscited by 21
  9. 2023Relationship between Model Compression and Adversarial Robustness: A Review of Current Evidencecited by 6
  10. 2022Channel Pruned YOLOv5-based Deep Learning Approach for Rapid and Accurate Outdoor Obstacles Detectioncited by 3
  11. 2022Integration of a systolic array based hardware accelerator into a DNN operator auto-tuning frameworkcited by 3
  12. 2023Model Compression Methods for YOLOv5: A Reviewcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2025FastFLUX: Pruning FLUX with Block-wise Replacement and Sandwich Trainingcited by 5
  2. 2025Enhanced Pruning Strategy for Multi-Component Neural Architectures Using Component-Aware Graph Analysiscited by 3
  3. 2024Efficient Edge AI: Deploying Convolutional Neural Networks on FPGA with the Gemmini Acceleratorcited by 1
  4. 2025COMponent-Aware Pruning for Accelerated Control Tasks in Latent Space Modelscited by 0