论文标题
对象探测器的无标签合成预处理
Label-Free Synthetic Pretraining of Object Detectors
论文作者
论文摘要
我们建议使用实例检测（实体检测）的新方法，合成优化的布局，以预处理对象检测器具有合成图像。我们的“固体”方法由两个主要组成部分组成：（1）使用具有优化场景布置的未标记的3D模型生成合成图像； （2）在“实例检测”任务上预修对象检测器 - 给定描绘对象的查询图像，检测目标图像中完全相同对象的所有实例。我们的方法不需要任何语义标签来进行预处理，并允许使用任意，不同的3D模型。对可可的实验表明，通过优化的数据生成和适当的预处理任务，合成数据可以是预处理对象探测器的高效数据。尤其是，对渲染图像进行预修会在实际图像上进行预处理，同时使用明显较少的计算资源来实现性能竞争。代码可在https://github.com/princeton-vl/solid上找到。
We propose a new approach, Synthetic Optimized Layout with Instance Detection (SOLID), to pretrain object detectors with synthetic images. Our "SOLID" approach consists of two main components: (1) generating synthetic images using a collection of unlabelled 3D models with optimized scene arrangement; (2) pretraining an object detector on "instance detection" task - given a query image depicting an object, detecting all instances of the exact same object in a target image. Our approach does not need any semantic labels for pretraining and allows the use of arbitrary, diverse 3D models. Experiments on COCO show that with optimized data generation and a proper pretraining task, synthetic data can be highly effective data for pretraining object detectors. In particular, pretraining on rendered images achieves performance competitive with pretraining on real images while using significantly less computing resources. Code is available at https://github.com/princeton-vl/SOLID.
