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 2106.03899cs.CV
收藏

基于移位变换学习的分布外检测

Shifting Transformation Learning for Out-of-Distribution Detection

NVIDIA(英伟达)

Sina Mohseni, Arash Vahdat, Jay Yadawa

摘要:

检测分布外(OOD)样本在开放世界和安全关键型应用(如自治系统和医疗保健)中起着关键作用。最近,自我监督的表示学习技术(通过对比学习和借口学习)已经显示出有效地提高OOD检测。然而,这种方法的一个主要问题是选择移位变换和借口任务,这取决于域内分布。在本文中,我们提出了一个简单的框架,利用移位变换学习设置来学习训练集的多个移位表示,以改进OOD检测。为了解决选择最佳移位变换和借口任务的问题,我们提出了一种简单的机制,用于自动选择变换并调节它们对表示学习的影响,而不需要任何OOD训练样本。在广泛的实验中,我们证明了我们的简单框架在几个图像数据集上的性能优于最先进的OOD检测模型。我们还描述了一个理想的OOD检测器的标准,为现实世界的应用,并证明了我们提出的技术对国家的最先进的OOD检测技术的功效。

英文摘要:

Detecting out-of-distribution (OOD) samples plays a key role in open-world and safety-critical applications such as autonomous systems and healthcare. Recently, self-supervised representation learning techniques (via contrastive learning and pretext learning) have shown effective in improving OOD detection. However, one major issue with such approaches is the choice of shifting transformations and pretext tasks which depends on the in-domain distribution. In this paper, we propose a simple framework that leverages a shifting transformation learning setting for learning multiple shifted representations of the training set for improved OOD detection. To address the problem of selecting optimal shifting transformation and pretext tasks, we propose a simple mechanism for automatically selecting the transformations and modulating their effect on representation learning without requiring any OOD training samples. In extensive experiments, we show that our simple framework outperforms state-of-the-art OOD detection models on several image datasets. We also characterize the criteria for a desirable OOD detector for real-world applications and demonstrate the efficacy of our proposed technique against state-of-the-art OOD detection techniques.

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。

↑