论文标题
在混乱的背景下提高对象检测和分类的学习有效性
Improving Learning Effectiveness For Object Detection and Classification in Cluttered Backgrounds
论文作者
论文摘要
通常，神经网络模型在均匀背景下使用大量图像进行训练。问题在于，在复杂且异构的环境中，受过训练的网络模型的性能可能会大大降低。为了减轻问题，本文开发了一个框架，该框架允许自主在异构混乱背景中自主生成训练数据集。显然，与典型数据集相比，在复杂和异质环境中，应在复杂和异构环境中提高所提出框架的学习有效性。在我们的框架中，一种称为deepLab的最先进的图像分割技术用于从图片中提取感兴趣的对象，然后使用色度键技术将感兴趣的对象合并为特定的异质背景。通过经验测试研究了提出的框架的性能，并将其与使用可可数据集训练的模型的性能进行了比较。结果表明，所提出的框架优于模型比较。这意味着开发的框架的学习有效性优于典型数据集的模型。
Usually, Neural Networks models are trained with a large dataset of images in homogeneous backgrounds. The issue is that the performance of the network models trained could be significantly degraded in a complex and heterogeneous environment. To mitigate the issue, this paper develops a framework that permits to autonomously generate a training dataset in heterogeneous cluttered backgrounds. It is clear that the learning effectiveness of the proposed framework should be improved in complex and heterogeneous environments, compared with the ones with the typical dataset. In our framework, a state-of-the-art image segmentation technique called DeepLab is used to extract objects of interest from a picture and Chroma-key technique is then used to merge the extracted objects of interest into specific heterogeneous backgrounds. The performance of the proposed framework is investigated through empirical tests and compared with that of the model trained with the COCO dataset. The results show that the proposed framework outperforms the model compared. This implies that the learning effectiveness of the framework developed is superior to the models with the typical dataset.
