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 2001.05419cs.LGcs.CVstat.ML
收藏

用于分布外检测的深层剩余流

Deep Residual Flow for Out of Distribution Detection

Technion(以色列理工学院)

Ev Zisselman, Aviv Tamar

摘要:

神经网络在现实世界中的有效应用依赖于熟练地检测分布外的例子。当代方法试图对训练数据中的特征激活的分布进行建模,以充分区分异常,并且现有技术的方法使用高斯分布模型。在这项工作中,我们提出了一种新的方法,通过利用基于规范化流的表达密度模型来改进最先进的方法。我们介绍了残差流,一种新的流架构,从基础高斯分布学习残差分布。我们的模型是通用的,可以应用于任何近似高斯的数据。对于图像数据集中的分布外检测,我们的方法提供了一个原则性的改进。具体来说,我们证明了我们的方法在各种图像数据集上训练的ResNet和DenseNet架构中的有效性。例如,在CIFAR-100上训练的ResNet上,并对ImageNet数据集的分布外样本进行检测评估,将真阳性率(TPR)保持在$95\%$,我们将真阴性率(TNR)从$56.7\%$(当前最先进的)提高到$77.5\%$(我们的)。

英文摘要:

The effective application of neural networks in the real-world relies on proficiently detecting out-of-distribution examples. Contemporary methods seek to model the distribution of feature activations in the training data for adequately distinguishing abnormalities, and the state-of-the-art method uses Gaussian distribution models. In this work, we present a novel approach that improves upon the state-of-the-art by leveraging an expressive density model based on normalizing flows. We introduce the residual flow, a novel flow architecture that learns the residual distribution from a base Gaussian distribution. Our model is general, and can be applied to any data that is approximately Gaussian. For out of distribution detection in image datasets, our approach provides a principled improvement over the state-of-the-art. Specifically, we demonstrate the effectiveness of our method in ResNet and DenseNet architectures trained on various image datasets. For example, on a ResNet trained on CIFAR-100 and evaluated on detection of out-of-distribution samples from the ImageNet dataset, holding the true positive rate (TPR) at $95\%$, we improve the true negative rate (TNR) from $56.7\%$ (current state-of-the-art) to $77.5\%$ (ours).

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。

↑