Building instance detection models that are data efficient and can handle rare object categories is an important challenge in computer vision. But data collection methods and metrics are lack of research towards real scenarios application using neural network. Here, we perform a systematic study of the Object Occlusion data collection and augmentation methods where we imitate object occlusion relationship in target scenarios. However, we find that the simple mechanism of object occlusion is good enough and can provide acceptable accuracy in real scenarios adding new category. We illustate that only adding 15 images of new category in a half million training dataset with hundreds categories, can give this new category 95% accuracy in unseen test dataset including thousands of images of this category.

翻译：建立数据高效且能够处理稀有对象类别的实例探测模型是计算机视觉中的一项重要挑战。 但是,数据收集方法和衡量尺度缺乏对使用神经网络的实际情景应用的研究。 在这里, 我们系统研究对象封闭性数据收集和增强方法, 在目标情景中模仿对象隔离关系。 然而, 我们发现, 简单的物体隔离机制已经足够好, 并且能够在真实情景中提供可接受的准确性, 添加新的类别。 我们没有说明, 仅仅在50万个培训数据集中添加15个新类别图像, 包含数百个类别的, 就可以在包括数千个此类图像的未知测试数据集中提供95%的准确性 。