A Novel Compression Framework for YOLOv8: Achieving Real-Time Aerial Object Detection on Edge Devices via Structured Pruning and Channel-Wise Distillation

• URL: http://arxiv.org/abs/2509.12918v2
• Date: Wed, 17 Sep 2025 12:59:25 GMT
• Title: A Novel Compression Framework for YOLOv8: Achieving Real-Time Aerial Object Detection on Edge Devices via Structured Pruning and Channel-Wise Distillation
• Authors: Melika Sabaghian, Mohammad Ali Keyvanrad, Seyyedeh Mahila Moghadami,
• Abstract summary: We propose a novel three-stage compression pipeline for the YOLOv8 object detection model.<n>Sparsity-aware training, structured channel pruning, and Channel-Wise Knowledge Distillation (CWD) are used.<n>Experiments on the VisDrone dataset demonstrate the effectiveness of our approach across multiple YOLOv8 variants.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Efficient deployment of deep learning models for aerial object detection on resource-constrained devices requires significant compression without com-promising performance. In this study, we propose a novel three-stage compression pipeline for the YOLOv8 object detection model, integrating sparsity-aware training, structured channel pruning, and Channel-Wise Knowledge Distillation (CWD). First, sparsity-aware training introduces dynamic sparsity during model optimization, effectively balancing parameter reduction and detection accuracy. Second, we apply structured channel pruning by leveraging batch normalization scaling factors to eliminate redundant channels, significantly reducing model size and computational complexity. Finally, to mitigate the accuracy drop caused by pruning, we employ CWD to transfer knowledge from the original model, using an adjustable temperature and loss weighting scheme tailored for small and medium object detection. Extensive experiments on the VisDrone dataset demonstrate the effectiveness of our approach across multiple YOLOv8 variants. For YOLOv8m, our method reduces model parameters from 25.85M to 6.85M (a 73.51% reduction), FLOPs from 49.6G to 13.3G, and MACs from 101G to 34.5G, while reducing AP50 by only 2.7%. The resulting compressed model achieves 47.9 AP50 and boosts inference speed from 26 FPS (YOLOv8m baseline) to 45 FPS, enabling real-time deployment on edge devices. We further apply TensorRT as a lightweight optimization step. While this introduces a minor drop in AP50 (from 47.9 to 47.6), it significantly improves inference speed from 45 to 68 FPS, demonstrating the practicality of our approach for high-throughput, re-source-constrained scenarios.

Related papers

• A Text-Guided Vision Model for Enhanced Recognition of Small Instances [0.0]
  An efficient text-guided object detection model has been developed to enhance the detection of small objects.<n>The proposed method replaces the C2f layer in the YOLOv8 backbone with a C3k2 layer, enabling more precise representation of local features.<n> Comparative experiments on the VisDrone dataset show that the proposed model outperforms the original YOLO-World model.
  arXiv  Detail & Related papers  (2026-02-23T04:40:14Z)
• MRS-YOLO Railroad Transmission Line Foreign Object Detection Based on Improved YOLO11 and Channel Pruning [2.6795746856835785]
  We propose an improved algorithm MRS-YOLO based on YOLO11.<n>The mAP50 and mAP50:95 of the MRS-YOLO algorithm are improved to 94.8% and 86.4%, respectively.
  arXiv  Detail & Related papers  (2025-10-12T11:38:09Z)
• YOLO-ROC: A High-Precision and Ultra-Lightweight Model for Real-Time Road Damage Detection [0.0]
  Road damage detection is a critical task for ensuring traffic safety and maintaining infrastructure integrity.<n>This paper proposes a high-precision and lightweight model, YOLO - Road Orthogonal Compact (YOLO-ROC)
  arXiv  Detail & Related papers  (2025-07-31T03:35:19Z)
• You Sense Only Once Beneath: Ultra-Light Real-Time Underwater Object Detection [2.5249064981269296]
  We propose an Ultra-Light Real-Time Underwater Object Detection framework, You Sense Only Once Beneath (YSOOB)<n>Specifically, we utilize a Multi-Spectrum Wavelet (MSWE) to perform frequency-domain encoding on the input image, minimizing the semantic loss caused by underwater optical color distortion.<n>We also eliminate model redundancy through a simple yet effective channel compression and reconstructed large kernel convolution (RLKC) to achieve model lightweight.
  arXiv  Detail & Related papers  (2025-04-22T08:26:35Z)
• A lightweight model FDM-YOLO for small target improvement based on YOLOv8 [0.0]
  Small targets are difficult to detect due to their low pixel count, complex backgrounds, and varying shooting angles.<n>This paper focuses on small target detection and explores methods for object detection under low computational constraints.
  arXiv  Detail & Related papers  (2025-03-06T14:06:35Z)
• LeYOLO, New Embedded Architecture for Object Detection [0.0]
  We introduce two key contributions to object detection models using MSCOCO as a base validation set.<n>First, we propose LeNeck, a general-purpose detection framework that maintains inference speed comparable to SSDLite.<n>Second, we present LeYOLO, an efficient object detection model designed to enhance computational efficiency in YOLO-based architectures.
  arXiv  Detail & Related papers  (2024-06-20T12:08:24Z)
• Data-Free Dynamic Compression of CNNs for Tractable Efficiency [46.498278084317704]
  structured pruning approaches have shown promise in lowering floating-point operations without substantial drops in accuracy.<n>We propose HASTE (Hashing for Tractable Efficiency), a data-free, plug-and-play convolution module that instantly reduces a network's test-time inference cost without training or fine-tuning.<n>We demonstrate our approach on the popular vision benchmarks CIFAR-10 and ImageNet, where we achieve a 46.72% reduction in FLOPs with only a 1.25% loss in accuracy.
  arXiv  Detail & Related papers  (2023-09-29T13:09:40Z)
• EdgeYOLO: An Edge-Real-Time Object Detector [69.41688769991482]
  This paper proposes an efficient, low-complexity and anchor-free object detector based on the state-of-the-art YOLO framework. We develop an enhanced data augmentation method to effectively suppress overfitting during training, and design a hybrid random loss function to improve the detection accuracy of small objects. Our baseline model can reach the accuracy of 50.6% AP50:95 and 69.8% AP50 in MS 2017 dataset, 26.4% AP50:95 and 44.8% AP50 in VisDrone 2019-DET dataset, and it meets real-time requirements (FPS>=30) on edge-computing device Nvidia
  arXiv  Detail & Related papers  (2023-02-15T06:05:14Z)
• Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance [68.8204255655161]
  We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We evaluate our algorithm across multiple quantized models that we train for different tasks, showing that our approach can reduce the precision of accumulators while maintaining model accuracy with respect to a floating-point baseline.
  arXiv  Detail & Related papers  (2023-01-31T02:46:57Z)
• Pushing the Limits of Asynchronous Graph-based Object Detection with Event Cameras [62.70541164894224]
  We introduce several architecture choices which allow us to scale the depth and complexity of such models while maintaining low computation. Our method runs 3.7 times faster than a dense graph neural network, taking only 8.4 ms per forward pass.
  arXiv  Detail & Related papers  (2022-11-22T15:14:20Z)
• Channel Pruned YOLOv5-based Deep Learning Approach for Rapid and Accurate Outdoor Obstacles Detection [6.703770367794502]
  One-stage algorithm have been widely used in target detection systems that need to be trained with massive data. Due to their convolutional structure, they need more computing power and greater memory consumption. We apply pruning strategy to target detection networks to reduce the number of parameters and the size of model.
  arXiv  Detail & Related papers  (2022-04-27T21:06:04Z)
• A lightweight and accurate YOLO-like network for small target detection in Aerial Imagery [94.78943497436492]
  We present YOLO-S, a simple, fast and efficient network for small target detection. YOLO-S exploits a small feature extractor based on Darknet20, as well as skip connection, via both bypass and concatenation. YOLO-S has an 87% decrease of parameter size and almost one half FLOPs of YOLOv3, making practical the deployment for low-power industrial applications.
  arXiv  Detail & Related papers  (2022-04-05T16:29:49Z)
• Non-Parametric Adaptive Network Pruning [125.4414216272874]
  We introduce non-parametric modeling to simplify the algorithm design. Inspired by the face recognition community, we use a message passing algorithm to obtain an adaptive number of exemplars. EPruner breaks the dependency on the training data in determining the "important" filters.
  arXiv  Detail & Related papers  (2021-01-20T06:18:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.