arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1810.02426cs.CV
收藏

相对显著性和排名:模型,数据,基准

Relative Saliency and Ranking: Models, Metrics, Data, and Benchmarks

University of Manitoba(曼尼托巴大学);Ryerson University(瑞尔森大学);Vector Institute(向量研究所)

Mahmoud Kalash, Md Amirul Islam, Neil D. B. Bruce

摘要:

显著目标检测是已经被详细考虑的问题,并且\textcolor{black}{many solutions have been proposed}。在本文中,我们认为,迄今为止的工作已经解决了一个问题,是相对不适定。具体来说,当多个观察者被询问时,关于什么构成显著对象并没有普遍的共识。这意味着一些对象比其他对象更有可能被判断为显著的,并且意味着显著对象上存在相对等级。首先,我们提出了一种新的深度学习解决方案,该解决方案基于相对显着性的分层表示和逐阶段细化。除此之外,我们还提出了数据,分析和基线基准结果,以解决显着对象排名的问题。用于获得合适的排名显着对象实例的方法,以及适合测量算法性能的度量。此外,我们还展示了如何对派生数据集进行连续优化,以提供与原始地面实况在其特征和训练和测试模型的价值方面具有良好相关性的清洁结果。最后,我们提供了一个比较流行的算法,解决显着的对象排名或检测,以建立初始基线提供一个基础,与未来的努力解决这个问题进行比较。\textcolor{black}{The source code and data are publicly available via our project page:} \textrm{\href{https://ryersonvisionlab.github.io/cocosalrank.html}{ryersonvisionlab.github.io/cocosalrank}}

英文摘要:

Salient object detection is a problem that has been considered in detail and \textcolor{black}{many solutions have been proposed}. In this paper, we argue that work to date has addressed a problem that is relatively ill-posed. Specifically, there is not universal agreement about what constitutes a salient object when multiple observers are queried. This implies that some objects are more likely to be judged salient than others, and implies a relative rank exists on salient objects. Initially, we present a novel deep learning solution based on a hierarchical representation of relative saliency and stage-wise refinement. Further to this, we present data, analysis and baseline benchmark results towards addressing the problem of salient object ranking. Methods for deriving suitable ranked salient object instances are presented, along with metrics suitable to measuring algorithm performance. In addition, we show how a derived dataset can be successively refined to provide cleaned results that correlate well with pristine ground truth in its characteristics and value for training and testing models. Finally, we provide a comparison among prevailing algorithms that address salient object ranking or detection to establish initial baselines providing a basis for comparison with future efforts addressing this problem. \textcolor{black}{The source code and data are publicly available via our project page:} \textrm{\href{https://ryersonvisionlab.github.io/cocosalrank.html}{ryersonvisionlab.github.io/cocosalrank}}

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。

↑