arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2208.06809cs.CV
收藏

多属性开集识别

Multi-Attribute Open Set Recognition

Bosch Center for Artificial Intelligence(博世人工智能中心);University of Freiburg(弗莱堡大学)

Piyapat Saranrittichai, Chaithanya Kumar Mummadi, Claudia Blaiotta, Mauricio Munoz, Volker Fischer

摘要:

开放集识别(OSR)通过同时分类已知类和识别未知类,将图像分类扩展到开放世界环境。虽然传统的OSR方法可以检测分布外(OOD)样本,但是它们不能提供指示哪个(哪些)底层视觉属性(例如,形状、颜色或背景)导致特定样品未知。在这项工作中,我们介绍了一种新的问题设置,将传统的OSR的多属性设置,多个视觉属性同时识别。在这里,OOD样本不仅可以被识别,而且可以通过它们的未知属性进行分类。我们提出了简单的扩展常见的OSR基线来处理这种新的情况。我们表明,当训练数据集中存在虚假相关性时,这些基线容易受到捷径的影响。这导致了糟糕的OOD性能,根据我们的实验,这主要是由于预测的置信度分数的非预期的跨属性相关性。我们提供的经验证据表明,这种行为在合成和真实世界数据集的不同基线上是一致的。

英文摘要:

Open Set Recognition (OSR) extends image classification to an open-world setting, by simultaneously classifying known classes and identifying unknown ones. While conventional OSR approaches can detect Out-of-Distribution (OOD) samples, they cannot provide explanations indicating which underlying visual attribute(s) (e.g., shape, color or background) cause a specific sample to be unknown. In this work, we introduce a novel problem setup that generalizes conventional OSR to a multi-attribute setting, where multiple visual attributes are simultaneously recognized. Here, OOD samples can be not only identified but also categorized by their unknown attribute(s). We propose simple extensions of common OSR baselines to handle this novel scenario. We show that these baselines are vulnerable to shortcuts when spurious correlations exist in the training dataset. This leads to poor OOD performance which, according to our experiments, is mainly due to unintended cross-attribute correlations of the predicted confidence scores. We provide an empirical evidence showing that this behavior is consistent across different baselines on both synthetic and real world datasets.

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。

↑