论文标题
在对象检测中添加新类别
Adding New Categories in Object Detection Using Few-Shot Copy-Paste
论文作者
论文摘要
开发可以处理稀有对象类别的数据有效实例检测模型仍然是计算机视觉中的关键挑战。但是，现有的研究通常忽略了数据收集策略和评估指标，该指标量身定制了涉及神经网络的现实情况。在这项研究中，我们系统地研究了针对物体闭塞的数据收集和增强技术，旨在模仿在实际应用中观察到的遮挡关系。令人惊讶的是，我们发现即使是一种简单的遮挡机制也足以在引入新对象类别时实现强大的性能。值得注意的是，通过在一个大规模培训数据集中仅添加15个新类别的图像，该数据集包含数百个类别的半百万张图像，该模型可以在不看到的测试集中达到95 \％的准确性，并具有成千上万个新类别实例。
Developing data-efficient instance detection models that can handle rare object categories remains a key challenge in computer vision. However, existing research often overlooks data collection strategies and evaluation metrics tailored to real-world scenarios involving neural networks. In this study, we systematically investigate data collection and augmentation techniques focused on object occlusion, aiming to mimic occlusion relationships observed in practical applications. Surprisingly, we find that even a simple occlusion mechanism is sufficient to achieve strong performance when introducing new object categories. Notably, by adding just 15 images of a new category to a large-scale training dataset containing over half a million images across hundreds of categories, the model achieves 95\% accuracy on an unseen test set with thousands of instances of the new category.
