Building neural network classifiers with an ability to distinguish between in and out-of distribution inputs is an important step towards faithful deep learning systems. Some of the successful approaches for this, resort to architectural novelties, such as ensembles, with increased complexities in terms of the number of parameters and training procedures. Whereas some other approaches make use of surrogate samples, which are easy to create and work as proxies for actual out-of-distribution (OOD) samples, to train the networks for OOD detection. In this paper, we propose a very simple approach for enhancing the ability of a pretrained network to detect OOD inputs without even altering the original parameter values. We define a probabilistic trust interval for each weight parameter of the network and optimize its size according to the in-distribution (ID) inputs. It allows the network to sample additional weight values along with the original values at the time of inference and use the observed disagreement among the corresponding outputs for OOD detection. In order to capture the disagreement effectively, we also propose a measure and establish its suitability using empirical evidence. Our approach outperforms the existing state-of-the-art methods on various OOD datasets by considerable margins without using any real or surrogate OOD samples. We also analyze the performance of our approach on adversarial and corrupted inputs such as CIFAR-10-C and demonstrate its ability to clearly distinguish such inputs as well. By using fundamental theorem of calculus on neural networks, we explain why our technique doesn't need to observe OOD samples during training to achieve results better than the previous works.
翻译:建立能够区分分配投入和分配外投入的神经网络分类系统是朝向忠实的深层次学习系统迈出的重要一步。在这方面,一些成功的方法是采用建筑创新方法,如建筑创新方法,如组合,在参数和培训程序数量方面更加复杂;而其他一些方法则使用代用样品,这些样品很容易产生,并且作为实际分配外(OOOD)样本的替代物,用来对OOOD检测网络进行培训。在本文中,我们提出一种非常简单的方法,用于加强预先训练的网络在不改变原始参数值的情况下检测OOOD投入的能力。我们确定网络每个重量参数的概率信任间隔,并根据分配(ID)投入优化其规模。它使网络能够取样更多的重量值,同时作为实际分配外(OOOD)样本的原始值,并使用观察到的对OOODO的检测结果之间的分歧。为了有效了解分歧,我们还提出一种衡量标准,并使用经验证据来确定其适合性。我们的方法比OOOOD基本投入的当前水平高得多。我们的方法在使用真正的OD(OD)模型分析方法时,不以更清楚地解释我们以前的任何数据分析。