arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.06509cs.CVcs.AI
收藏

在开放和封闭设置中解决视觉搜索

Addressing Visual Search in Open and Closed Set Settings

The Johns Hopkins University Applied Physics Laboratory(约翰霍普金斯大学应用物理实验室)

Nathan Drenkow, Philippe Burlina, Neil Fendley, Onyekachi Odoemene, Jared Markowitz

摘要:

在大图像中搜索小对象对于当前的深度学习系统来说是一项具有挑战性的任务,但在许多现实世界的应用中(如遥感和医学成像)却非常重要。彻底扫描非常大的图像在计算上是昂贵的,特别是在足以捕获小物体的分辨率下。感兴趣的对象越小,它就越有可能被杂乱所掩盖,或者被认为是无关紧要的。我们研究这些问题的背景下,两个互补的问题:闭集目标检测和开集目标搜索。首先,我们提出了一种方法,用于预测像素级的对象从低分辨率的要点图像,然后我们使用它来选择区域执行目标检测本地高分辨率。这种方法的好处是不固定到预定的网格,从而需要比现有方法更少的昂贵的高分辨率的一瞥。其次,我们提出了一种新的策略,开放集的视觉搜索,旨在找到所有的目标类,这可能是以前看不见的,是由一个单一的图像定义的实例。我们解释这两个检测问题,通过概率,贝叶斯透镜,从而由我们的方法产生的对象地图作为先验的最大后验方法的检测步骤。我们评估了端到端的性能,我们的补丁选择策略与这种目标搜索方法的组合,我们的补丁选择策略与标准的目标检测方法的组合。我们的方法的两个要素被认为是显着优于基线策略。

英文摘要:

Searching for small objects in large images is a task that is both challenging for current deep learning systems and important in numerous real-world applications, such as remote sensing and medical imaging. Thorough scanning of very large images is computationally expensive, particularly at resolutions sufficient to capture small objects. The smaller an object of interest, the more likely it is to be obscured by clutter or otherwise deemed insignificant. We examine these issues in the context of two complementary problems: closed-set object detection and open-set target search. First, we present a method for predicting pixel-level objectness from a low resolution gist image, which we then use to select regions for performing object detection locally at high resolution. This approach has the benefit of not being fixed to a predetermined grid, thereby requiring fewer costly high-resolution glimpses than existing methods. Second, we propose a novel strategy for open-set visual search that seeks to find all instances of a target class which may be previously unseen and is defined by a single image. We interpret both detection problems through a probabilistic, Bayesian lens, whereby the objectness maps produced by our method serve as priors in a maximum-a-posteriori approach to the detection step. We evaluate the end-to-end performance of both the combination of our patch selection strategy with this target search approach and the combination of our patch selection strategy with standard object detection methods. Both elements of our approach are seen to significantly outperform baseline strategies.

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。

↑