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 2203.07798stat.MLcs.LG
收藏

Igeood:一种信息几何的分布外检测方法

Igeood: An Information Geometry Approach to Out-of-Distribution Detection

Laboratoire des signaux et systèmes (L2S)(信号与系统实验室);Université Paris-Saclay(巴黎萨克雷大学);CNRS(法国国家科学研究中心);CentraleSupélec(巴黎中央理工-高等电力学院);International Laboratory on Learning Systems (ILLS)(学习系统国际实验室);McGill(麦吉尔大学);ETS(蒙特利尔高等技术学院);MILA(蒙特利尔学习算法研究所)

Eduardo Dadalto Camara Gomes, Florence Alberge, Pierre Duhamel, Pablo Piantanida

摘要:

可靠的分发外(OOD)检测是实现更安全的现代机器学习(ML)系统的基础。在本文中,我们介绍了Igood,一种有效的方法来检测OOD样本。Igeood适用于任何预先训练的神经网络,在不同程度的ML模型访问下工作,不需要OOD样本或对OOD数据的假设,但也可以从OOD样本中受益(如果可用)。通过构建底层数据分布之间的测地线(Fisher-Rao)距离,我们的神经网络可以将logits输出的置信度得分与深度神经网络的学习特征相结合。从经验上讲,我们表明Igeood在各种网络架构和数据集上的表现优于竞争对手的最先进的方法。

英文摘要:

Reliable out-of-distribution (OOD) detection is fundamental to implementing safer modern machine learning (ML) systems. In this paper, we introduce Igeood, an effective method for detecting OOD samples. Igeood applies to any pre-trained neural network, works under various degrees of access to the ML model, does not require OOD samples or assumptions on the OOD data but can also benefit (if available) from OOD samples. By building on the geodesic (Fisher-Rao) distance between the underlying data distributions, our discriminator can combine confidence scores from the logits outputs and the learned features of a deep neural network. Empirically, we show that Igeood outperforms competing state-of-the-art methods on a variety of network architectures and 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。

↑