Abstract
The You Only Look Once (YOLO) architecture is crucial for real-time object detection. However, deploying it in resource-constrained environments such as unmanned aerial vehicles (UAVs) requires efficient transfer learning. Although layer freezing is a common technique, the specific impact of various freezing configurations on contemporary YOLOv8 and YOLOv10 architectures remains unexplored, particularly with regard to the interplay between freezing depth, dataset characteristics, and training dynamics. This research addresses this gap by presenting a detailed analysis of layer-freezing strategies. We systematically investigate multiple freezing configurations across YOLOv8 and YOLOv10 variants using four challenging datasets that represent critical infrastructure monitoring. Our methodology integrates a gradient behavior analysis (L2 norm) and visual explanations (Grad-CAM) to provide deeper insights into training dynamics under different freezing strategies. Our results reveal that there is no universal optimal freezing strategy but, rather, one that depends on the properties of the data. For example, freezing the backbone is effective for preserving general-purpose features, while a shallower freeze is better suited to handling extreme class imbalance. These configurations reduce graphics processing unit (GPU) memory consumption by up to 28% compared to full fine-tuning and, in some cases, achieve mean average precision (mAP@50) scores that surpass those of full fine-tuning. Gradient analysis corroborates these findings, showing distinct convergence patterns for moderately frozen models. Ultimately, this work provides empirical findings and practical guidelines for selecting freezing strategies. It offers a practical, evidence-based approach to balanced transfer learning for object detection in scenarios with limited resources.
Abstract (translated)
仅此一次看（YOLO）架构对于实时目标检测至关重要。然而，在资源受限的环境中（如无人驾驶飞行器[UAV]）部署它需要高效的迁移学习。尽管冻结层是一种常见的技术，但不同冻结配置对当代YOLOv8和YOLOv10架构的具体影响尚未得到充分研究，尤其是在冻结深度、数据集特征以及训练动态之间的相互作用方面。这项研究通过详细分析层冻结策略来填补这一空白。我们系统地调查了YOLOv8和YOLOv10变体中多种冻结配置，并使用四个具有挑战性的代表关键基础设施监控的数据集进行测试。我们的方法结合了梯度行为分析（L2范数）和视觉解释（Grad-CAM），以在不同冻结策略下提供对训练动态的更深入了解。研究结果表明，没有通用的最佳冻结策略，而是根据数据属性有所不同。例如，冻结骨干网络有助于保持一般特征的有效性，而浅层冻结则更适合处理极端类别不平衡的情况。这些配置与全面微调相比可减少多达28%的图形处理器（GPU）内存消耗，并在某些情况下实现超过全面微调的平均精度均值（mAP@50）分数。梯度分析证实了这一发现，展示了适度冻结模型的独特收敛模式。最终，这项工作提供了经验性发现和实用指南来选择冻结策略。它为资源有限场景中的目标检测平衡迁移学习提供了一种基于证据的实际方法。
URL
https://arxiv.org/abs/2509.05490
