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 2005.14140cs.CV
收藏

用于异常检测的预训练深度特征中的正常数据分布建模

Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection

Institute of Imaging & Computer Vision(成像与计算机视觉研究所);RWTH Aachen University(亚琛工业大学)

Oliver Rippel, Patrick Mertens, Dorit Merhof

摘要:

图像中的异常检测(AD)是一个基本的计算机视觉问题,是指识别明显偏离标准的图像和图像子结构。流行的AD算法通常尝试使用任务特定的数据集从头开始学习正态模型,但由于大规模异常的不可访问性以及异常外观的模糊性,因此仅限于采用大多数正常数据的半监督方法。我们遵循另一种方法,并证明了在大型自然图像数据集上通过判别模型学习的深度特征表示非常适合描述正常性,并在迁移学习设置中检测甚至细微的异常。我们的正态模型是通过将多变量高斯(MVG)拟合到仅使用正常数据在ImageNet上训练的分类网络的深度特征表示来建立的。通过随后应用Mahalanobis距离作为异常评分,我们在公共MVTec AD数据集上的表现优于当前最先进的技术,在所有15个类别上实现了$95.8 \pm 1.2$的AUROC值(平均值$\pm$ SEM)。我们进一步研究为什么学习的表示是歧视性的AD任务,使用主成分分析。我们发现,在正常的数据中包含小的方差的主成分是区分正常和异常的情况下的关键。这为仅使用正常数据从头开始训练的AD方法的通常低于标准的性能提供了可能的解释。通过选择性地将MVG仅拟合到这些最相关的组件,我们能够进一步降低模型复杂性,同时保持AD性能。我们还研究了通过基于MVG假设选择可接受的假阳性率阈值来设置工作点。代码可在https://github.com/ORippler/gaussian-ad-mvtec获得

英文摘要:

Anomaly Detection (AD) in images is a fundamental computer vision problem and refers to identifying images and image substructures that deviate significantly from the norm. Popular AD algorithms commonly try to learn a model of normality from scratch using task specific datasets, but are limited to semi-supervised approaches employing mostly normal data due to the inaccessibility of anomalies on a large scale combined with the ambiguous nature of anomaly appearance. We follow an alternative approach and demonstrate that deep feature representations learned by discriminative models on large natural image datasets are well suited to describe normality and detect even subtle anomalies in a transfer learning setting. Our model of normality is established by fitting a multivariate Gaussian (MVG) to deep feature representations of classification networks trained on ImageNet using normal data only. By subsequently applying the Mahalanobis distance as the anomaly score we outperform the current state of the art on the public MVTec AD dataset, achieving an AUROC value of $95.8 \pm 1.2$ (mean $\pm$ SEM) over all 15 classes. We further investigate why the learned representations are discriminative to the AD task using Principal Component Analysis. We find that the principal components containing little variance in normal data are the ones crucial for discriminating between normal and anomalous instances. This gives a possible explanation to the often sub-par performance of AD approaches trained from scratch using normal data only. By selectively fitting a MVG to these most relevant components only, we are able to further reduce model complexity while retaining AD performance. We also investigate setting the working point by selecting acceptable False Positive Rate thresholds based on the MVG assumption. Code available at https://github.com/ORippler/gaussian-ad-mvtec

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。

↑