arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.05496cs.CV
收藏

学习变换减少目标检测中的几何偏移

Learning Transformations To Reduce the Geometric Shift in Object Detection

EPFL(洛桑联邦理工学院);ClearSpace SA(ClearSpace公司)

Vidit Vidit, Martin Engilberge, Mathieu Salzmann

摘要:

当测试分布与训练分布不同时,现代目标检测器的性能下降。解决这个问题的大多数方法都集中在对象外观变化上,例如,不同的照明条件,或合成图像和真实图像之间的间隙。在这里,相比之下,我们处理的几何变化出现在图像捕捉过程中,或由于环境的约束,导致内容本身的外观几何形状的差异。我们引入了一种自训练方法,该方法学习一组几何变换,以最大限度地减少这些偏移,而无需利用新领域中的任何标记数据,也无需利用有关相机的任何信息。我们在两个不同的班次上评估我们的方法,即,相机的视场(FoV)改变和视点改变。我们的研究结果表明,学习几何变换有助于检测器在目标域中表现得更好。

英文摘要:

The performance of modern object detectors drops when the test distribution differs from the training one. Most of the methods that address this focus on object appearance changes caused by, e.g., different illumination conditions, or gaps between synthetic and real images. Here, by contrast, we tackle geometric shifts emerging from variations in the image capture process, or due to the constraints of the environment causing differences in the apparent geometry of the content itself. We introduce a self-training approach that learns a set of geometric transformations to minimize these shifts without leveraging any labeled data in the new domain, nor any information about the cameras. We evaluate our method on two different shifts, i.e., a camera's field of view (FoV) change and a viewpoint change. Our results evidence that learning geometric transformations helps detectors to perform better in the target domains.

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。

↑