arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.04563cs.CVcs.LG
收藏

仿射子空间中的深度多标签分类

Deep Multi Label Classification in Affine Subspaces

University of Bern(伯尔尼大学);University Hospital of Bern(伯尔尼大学医院)

Thomas Kurmann, Pablo Marquez Neila, Sebastian Wolf, Raphael Sznitman

摘要:

多标签分类(MLC)问题在医学成像领域越来越受欢迎。这在一定程度上是由以下事实驱动的:为MLC获取注释远不如为语义分割获取注释那么繁重,并且还提供了比多类分类更多的表现力。然而,为了训练MLC,大多数方法都采用了与传统多类分类设置类似的目标函数。我们在这项工作中表明,这种方法不是最佳的,而是提出了一种新的深MLC分类方法在仿射子空间。在其核心,该方法试图将类别标签的特征拉向不同的仿射子空间,同时最大化它们之间的距离。我们使用两个MLC医学成像数据集的方法进行评估,并显示出较大的性能提高相比,以前的多标签框架。该方法可以被视为插件替换损失函数,并且可以以端到端的方式进行训练。

英文摘要:

Multi-label classification (MLC) problems are becoming increasingly popular in the context of medical imaging. This has in part been driven by the fact that acquiring annotations for MLC is far less burdensome than for semantic segmentation and yet provides more expressiveness than multi-class classification. However, to train MLCs, most methods have resorted to similar objective functions as with traditional multi-class classification settings. We show in this work that such approaches are not optimal and instead propose a novel deep MLC classification method in affine subspace. At its core, the method attempts to pull features of class-labels towards different affine subspaces while maximizing the distance between them. We evaluate the method using two MLC medical imaging datasets and show a large performance increase compared to previous multi-label frameworks. This method can be seen as a plug-in replacement loss function and is trainable in an end-to-end fashion.

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。

↑