论文标题
基于元认知的简单有效的对象检测方法
Meta-Cognition-Based Simple And Effective Approach To Object Detection
论文作者
论文摘要
最近，许多研究人员试图在准确性和操作速度方面改善基于深度学习的对象检测模型。但是，经常，此类模型的速度和准确性之间存在权衡，这阻碍了它们在自动导航等实际应用中的使用。在本文中，我们探讨了一种元认知学习策略，以提高对象检测能力，同时保持检测速度。元认知方法选择性地示例训练数据集中的对象实例以减少过度拟合。我们使用Yolo V3 Tiny作为工作的基础模型，并使用MS Coco数据集评估性能。实验结果表明，绝对精度的提高为2.6％（最小）和4.4％（最大），没有推理时间开销。
Recently, many researchers have attempted to improve deep learning-based object detection models, both in terms of accuracy and operational speeds. However, frequently, there is a trade-off between speed and accuracy of such models, which encumbers their use in practical applications such as autonomous navigation. In this paper, we explore a meta-cognitive learning strategy for object detection to improve generalization ability while at the same time maintaining detection speed. The meta-cognitive method selectively samples the object instances in the training dataset to reduce overfitting. We use YOLO v3 Tiny as a base model for the work and evaluate the performance using the MS COCO dataset. The experimental results indicate an improvement in absolute precision of 2.6% (minimum), and 4.4% (maximum), with no overhead to inference time.
