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 1708.07522cs.CV
收藏

SPARCNN:空间相关的卷积神经网络

SPARCNN: SPAtially Related Convolutional Neural Networks

Knexus Research Corporation(Knexus研究公司);Naval Research Laboratory(海军研究实验室)

JT Turner, Kalyan Moy Gupta, David Aha

摘要:

在杂乱场景中以不同像素大小准确检测和分类物体的能力对许多海军应用至关重要。然而,当应用于这种杂乱和多目标检测任务时,诸如卷积神经网络(CNN)的现有技术方法的检测性能降低并受到影响。我们推测,可以利用图像中对象之间的空间关系来显着提高检测精度,这是一种在进行研究时尚未被任何现有技术(据我们所知)考虑的方法。我们介绍了一种称为空间相关检测与卷积神经网络(SPARCNN)的检测和分类技术,该技术学习并利用来自训练集的图像中对象间空间配置的概率表示,以获得更有效的区域建议,以与最先进的CNN一起使用。我们对SPARCNN在VOC 2007数据集上的经验评估表明,与不利用空间关系的区域建议技术相比,它将分类准确率提高了8%。更重要的是,当测试集中的任务难度增加时,我们获得了18.8%的更高性能提升,包括高度模糊的物体和增加的图像混乱。

英文摘要:

The ability to accurately detect and classify objects at varying pixel sizes in cluttered scenes is crucial to many Navy applications. However, detection performance of existing state-of the-art approaches such as convolutional neural networks (CNNs) degrade and suffer when applied to such cluttered and multi-object detection tasks. We conjecture that spatial relationships between objects in an image could be exploited to significantly improve detection accuracy, an approach that had not yet been considered by any existing techniques (to the best of our knowledge) at the time the research was conducted. We introduce a detection and classification technique called Spatially Related Detection with Convolutional Neural Networks (SPARCNN) that learns and exploits a probabilistic representation of inter-object spatial configurations within images from training sets for more effective region proposals to use with state-of-the-art CNNs. Our empirical evaluation of SPARCNN on the VOC 2007 dataset shows that it increases classification accuracy by 8% when compared to a region proposal technique that does not exploit spatial relations. More importantly, we obtained a higher performance boost of 18.8% when task difficulty in the test set is increased by including highly obscured objects and increased image clutter.

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。

↑