一种新的压缩框架用于YOLOv8：通过结构化剪枝和通道级知识蒸馏实现边缘设备上的实时空中目标检测
A Novel Compression Framework for YOLOv8: Achieving Real-Time Aerial Object Detection on Edge Devices via Structured Pruning and Channel-Wise Distillation
AI总结：
本文提出了一种新的压缩框架，通过结构化剪枝和通道级知识蒸馏，有效压缩YOLOv8模型，实现边缘设备上的实时空中目标检测。
摘要：
在资源受限设备上高效部署深度学习模型进行空中目标检测需要显著压缩，同时不损害性能。在本研究中，我们提出了一种新的三阶段压缩管道，用于YOLOv8目标检测模型，集成了稀疏感知训练、结构化通道剪枝和通道级知识蒸馏（CWD）。首先，稀疏感知训练在模型优化过程中引入动态稀疏性，有效平衡参数减少和检测准确性。其次，我们通过利用批量归一化缩放因子应用结构化通道剪枝，消除冗余通道，显著减少模型大小和计算复杂性。最后，为了缓解剪枝导致的准确性下降，我们采用CWD将知识从原始模型转移过来，使用可调节的温度和损失加权方案，专门针对小和中等目标检测。在VisDrone数据集上的广泛实验表明，我们的方法在多个YOLOv8变体上都有效。对于YOLOv8m，我们的方法将模型参数从25.85M减少到6.85M（减少73.51%），FLOPs从49.6G减少到13.3G，MACs从101G减少到34.5G，同时AP50仅减少2.7%。所得到的压缩模型实现了47.9 AP50，并将推理速度从26 FPS（YOLOv8m基准）提升到45 FPS，使边缘设备上的实时部署成为可能。我们进一步应用TensorRT作为轻量级优化步骤。虽然这导致AP50略有下降（从47.9到47.6），但显著将推理速度从45提升到68 FPS，证明了我们的方法在高吞吐量、资源受限场景中的实用性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
