arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.06753cs.CV
收藏

学习开放世界的对象建议,而不学习分类

Learning Open-World Object Proposals without Learning to Classify

KAIST(韩国科学技术院);Google Brain(谷歌大脑)

Dahun Kim, Tsung-Yi Lin, Anelia Angelova, In So Kweon, Weicheng Kuo

摘要:

目标检测已经成为目标检测、弱监督检测、目标发现、跟踪等视觉流程中不可或缺的预处理步骤。与无学习方法相比,由于人们对目标检测的兴趣越来越大,基于学习的目标检测方法最近变得流行起来。常见的范例是从标记有一组对象区域及其相应类别的数据中学习对象建议。然而,这种方法经常与训练集中不存在的开放世界中的新对象进行斗争。在本文中,我们发现问题在于现有建议方法中的二进制分类器倾向于过拟合训练类别。因此,我们提出了一种无分类的对象定位网络(OLN),它纯粹通过区域的位置和形状与任何地面真实对象(例如,中心和IoU)。这个简单的策略学习了可概括的对象,并优于COCO上现有的跨类别概括建议,以及RoboNet,Object365和EpicKitchen上的跨数据集评估。最后,我们证明了OLN的优点长尾目标检测的大词汇量数据集,LVIS,我们注意到在罕见和常见的类别有明显的改善。

英文摘要:

Object proposals have become an integral preprocessing steps of many vision pipelines including object detection, weakly supervised detection, object discovery, tracking, etc. Compared to the learning-free methods, learning-based proposals have become popular recently due to the growing interest in object detection. The common paradigm is to learn object proposals from data labeled with a set of object regions and their corresponding categories. However, this approach often struggles with novel objects in the open world that are absent in the training set. In this paper, we identify that the problem is that the binary classifiers in existing proposal methods tend to overfit to the training categories. Therefore, we propose a classification-free Object Localization Network (OLN) which estimates the objectness of each region purely by how well the location and shape of a region overlap with any ground-truth object (e.g., centerness and IoU). This simple strategy learns generalizable objectness and outperforms existing proposals on cross-category generalization on COCO, as well as cross-dataset evaluation on RoboNet, Object365, and EpicKitchens. Finally, we demonstrate the merit of OLN for long-tail object detection on large vocabulary dataset, LVIS, where we notice clear improvement in rare and common categories.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑