论文标题
多尺度分数检测
Multiscale Score Matching for Out-of-Distribution Detection
论文作者
论文摘要
我们提出了一种新的方法，用于通过利用在多个噪声尺度上的分数估计的规范来检测分布外（OOD）图像。相对于输入数据，得分定义为对数密度的梯度。我们的方法完全不受监督，并遵循直接的训练计划。首先，我们训练一个深层网络以估计噪声水平的得分。训练后，我们计算N分布样本的嘈杂分数估计值，并在输入维度上采用L2-Norms（导致NXL矩阵）。然后，我们训练一个辅助模型（例如高斯混合模型），以学习该L维空间中的分布空间区域。现在，该辅助模型现在可用于识别位于学习空间之外的点。尽管它很简单，但我们的实验表明，该方法在检测分布外图像方面的表现明显优于最先进的图像。例如，我们的方法可以有效地将CIFAR-10（Inlier）和SVHN（OOD）图像分开，该设置以前已被证明对于深型可能模型而言很难。
We present a new methodology for detecting out-of-distribution (OOD) images by utilizing norms of the score estimates at multiple noise scales. A score is defined to be the gradient of the log density with respect to the input data. Our methodology is completely unsupervised and follows a straight forward training scheme. First, we train a deep network to estimate scores for levels of noise. Once trained, we calculate the noisy score estimates for N in-distribution samples and take the L2-norms across the input dimensions (resulting in an NxL matrix). Then we train an auxiliary model (such as a Gaussian Mixture Model) to learn the in-distribution spatial regions in this L-dimensional space. This auxiliary model can now be used to identify points that reside outside the learned space. Despite its simplicity, our experiments show that this methodology significantly outperforms the state-of-the-art in detecting out-of-distribution images. For example, our method can effectively separate CIFAR-10 (inlier) and SVHN (OOD) images, a setting which has been previously shown to be difficult for deep likelihood models.
