论文标题
用于在分布外检测中使用特征标准的块选择方法
Block Selection Method for Using Feature Norm in Out-of-distribution Detection
论文作者
论文摘要
在推理阶段检测分布（OOD）输入对于在现实世界中部署神经网络至关重要。以前的方法通常取决于从高度激活的特征图中得出的网络的输出。在这项研究中，我们首先揭示了从另一个块中获得的特征图的规范，而不是最后一个块可以更好地指示OOD检测。在此的动机上，我们提出了一个简单的框架，该框架由特征型：特征映射和Normratio的标准组成：ID和OOD的特征性比率，以测量每个块的OOD检测性能。特别是，为了选择提供ID特征和特征性特征型在ood的特征型之间最大差异的块，我们创建了拼图拼图图像作为ID训练样本的伪OOD并计算Normratio，并且选择了最大值的块。选择合适的块之后，通过特征型的OOD检测优于其他OOD检测方法，通过在CIFAR10基准上将FPR95降低高达52.77％，并且在Imagenet基准上最多可达48.53％。我们证明，我们的框架可以推广到各种体系结构和块选择的重要性，这也可以改善以前的OOD检测方法。
Detecting out-of-distribution (OOD) inputs during the inference stage is crucial for deploying neural networks in the real world. Previous methods commonly relied on the output of a network derived from the highly activated feature map. In this study, we first revealed that a norm of the feature map obtained from the other block than the last block can be a better indicator of OOD detection. Motivated by this, we propose a simple framework consisting of FeatureNorm: a norm of the feature map and NormRatio: a ratio of FeatureNorm for ID and OOD to measure the OOD detection performance of each block. In particular, to select the block that provides the largest difference between FeatureNorm of ID and FeatureNorm of OOD, we create Jigsaw puzzle images as pseudo OOD from ID training samples and calculate NormRatio, and the block with the largest value is selected. After the suitable block is selected, OOD detection with the FeatureNorm outperforms other OOD detection methods by reducing FPR95 by up to 52.77% on CIFAR10 benchmark and by up to 48.53% on ImageNet benchmark. We demonstrate that our framework can generalize to various architectures and the importance of block selection, which can improve previous OOD detection methods as well.
