We show that classifiers trained with random region proposals achieve state-of-the-art Open-world Object Detection (OWOD): they can not only maintain the accuracy of the known objects (w/ training labels), but also considerably improve the recall of unknown ones (w/o training labels). Specifically, we propose RandBox, a Fast R-CNN based architecture trained on random proposals at each training iteration, surpassing existing Faster R-CNN and Transformer based OWOD. Its effectiveness stems from the following two benefits introduced by randomness. First, as the randomization is independent of the distribution of the limited known objects, the random proposals become the instrumental variable that prevents the training from being confounded by the known objects. Second, the unbiased training encourages more proposal explorations by using our proposed matching score that does not penalize the random proposals whose prediction scores do not match the known objects. On two benchmarks: Pascal-VOC/MS-COCO and LVIS, RandBox significantly outperforms the previous state-of-the-art in all metrics. We also detail the ablations on randomization and loss designs. Codes are available at https://github.com/scuwyh2000/RandBox.

翻译：我们证明，使用随机区域提议训练的分类器在开放世界物体检测（OWOD）任务上达到了当前最优性能：它们不仅能保持已知物体（有训练标签）的检测精度，还显著提升了未知物体（无训练标签）的召回率。具体而言，我们提出了RandBox——一个基于Fast R-CNN的架构，每次训练迭代均使用随机提议进行训练，其性能超越了现有的基于Faster R-CNN和Transformer的OWOD方法。随机性带来的以下两个优势是其有效性的根源：第一，由于随机化过程独立于有限已知物体的分布，随机提议成为工具变量，避免了训练过程受已知物体混淆影响；第二，无偏训练通过采用所提出的匹配分数鼓励更多提议探索——该分数不会因随机提议的预测分数与已知物体不匹配而对其进行惩罚。在Pascal-VOC/MS-COCO和LVIS两个基准测试中，RandBox在所有指标上均显著优于此前最优方法。我们还详细开展了随机化策略与损失函数设计的消融研究。代码已开源至https://github.com/scuwyh2000/RandBox。