mlsanityData to 14 Oct 2026

Model Compression Methods for YOLOv5: A Review

arXiv 2307.11904 ↗First posted 21 Jul 2023cs.CV cs.LG cs.NEcited by 2

Not on the map. Why?

Abstract (arXiv)

Over the past few years, extensive research has been devoted to enhancing YOLO object detectors. Since its introduction, eight major versions of YOLO have been introduced with the purpose of improving its accuracy and efficiency. While the evident merits of YOLO have yielded to its extensive use in many areas, deploying it on resource-limited devices poses challenges. To address this issue, various neural network compression methods have been developed, which fall under three main categories, namely network pruning, quantization, and knowledge distillation. The fruitful outcomes of utilizing model compression methods, such as lowering memory usage and inference time, make them favorable, if not necessary, for deploying large neural networks on hardware-constrained edge devices. In this review paper, our focus is on pruning and quantization due to their comparative modularity. We categorize them and analyze the practical results of applying those methods to YOLOv5. By doing so, we identify gaps in adapting pruning and quantization for compressing YOLOv5, and provide future directions in this area for further exploration. Among several versions of YOLO, we specifically choose YOLOv5 for its excellent trade-off between recency and popularity in literature. This is the first specific review paper that surveys pruning and quantization methods from an implementation point of view on YOLOv5. Our study is also extendable to newer versions of YOLO as implementing them on resource-limited devices poses the same challenges that persist even today. This paper targets those interested in the practical deployment of model compression methods on YOLOv5, and in exploring different compression techniques that can be used for subsequent versions of YOLO.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 51 of its 106 references that are in the map. First posted on arXiv 21 Jul 2023.

Builds on

51 of 106 references.

References · 51

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  6. 2015Fast R-CNNcited by 2,933
  7. 2018YOLOv3: An Incremental Improvementcited by 2,659
  8. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  9. 2019Searching for MobileNetV3cited by 1,994
  10. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  11. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  12. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
38 more
  1. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  2. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  3. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  4. 2018Path Aggregation Network for Instance Segmentationcited by 798
  5. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 702
  6. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
  7. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 621
  8. 2018Object Detection with Deep Learning: A Reviewcited by 528
  9. 2021Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networkscited by 527
  10. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 522
  11. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  12. 2019CSPNet: A New Backbone that can Enhance Learning Capability of CNNcited by 381
  13. 2014Deeply-Supervised Netscited by 367
  14. 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 292
  15. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 275
  16. 2020Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluationcited by 188
  17. 2020TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systemscited by 165
  18. 2015Structured Pruning of Deep Convolutional Neural Networkscited by 149
  19. 2019Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networkscited by 148
  20. 2019Deep Learning in Video Multi-Object Tracking: A Surveycited by 107
  21. 2019A Survey of Deep Learning-based Object Detectioncited by 106
  22. 2021Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Maskscited by 103
  23. 2019Loss Aware Post-training Quantizationcited by 97
  24. 2020Channel Pruning via Automatic Structure Searchcited by 85
  25. 2020EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruningcited by 80
  26. 2021Only Train Once: A One-Shot Neural Network Training And Pruning Frameworkcited by 70
  27. 2022YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Losscited by 68
  28. 2018Compressing Neural Networks using the Variational Information Bottleneckcited by 59
  29. 2019AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Ratescited by 49
  30. 2021Learnable Companding Quantization for Accurate Low-bit Neural Networkscited by 42
  31. 2022SPDY: Accurate Pruning with Speedup Guaranteescited by 36
  32. 2019Non-Structured DNN Weight Pruning -- Is It Beneficial in Any Platform?cited by 32
  33. 2014Memory Bounded Deep Convolutional Networkscited by 17
  34. 2021Neural Network Quantization for Efficient Inference: A Surveycited by 14
  35. 2023A Unified Framework for Soft Threshold Pruningcited by 12
  36. 2022Accelerating Deep Learning Model Inference on Arm CPUs with Ultra-Low Bit Quantization and Runtimecited by 6
  37. 2019Single-shot Channel Pruning Based on Alternating Direction Method of Multiplierscited by 3
  38. 2022Channel Pruned YOLOv5-based Deep Learning Approach for Rapid and Accurate Outdoor Obstacles Detectioncited by 3

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 2.

2 papers.

  1. 2024Advancing Pavement Distress Detection in Developing Countries: A Novel Deep Learning Approach with Locally-Collected Datasetscited by 5
  2. 2024Iterative Filter Pruning for Concatenation-based CNN Architecturescited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2024Quantizing YOLOv7: A Comprehensive Study
  2. 2021Compressed Object Detection
  3. 2025A Novel Compression Framework for YOLOv8: Achieving Real-Time Aerial Object Detection on Edge Devices via Structured Pruning and Channel-Wise Distillation
  4. 2024Edge AI: Evaluation of Model Compression Techniques for Convolutional Neural Networks
  5. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Survey
  6. 2026Hybrid Compression: Integrating Pruning and Quantization for Optimized Neural Networks
  7. 2025Efficient compression of neural networks and datasets
  8. 2023Towards Optimal Compression: Joint Pruning and Quantization