论文标题
DFR：无监督异常分割的深度重建
DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation
论文作者
论文摘要
自动检测在没有异常先验的物体或纹理图像中的异常区域是具有挑战性的，尤其是当异常出现在非常小的图像区域中时，难以检测视觉变化，例如制造产品的缺陷。本文提出了一种有效的无监督异常分割方法，该方法可以检测和分割图像的小和密闭区域中的异常。具体而言，我们开发了一个多尺度的区域特征生成器，该生成器可以从图像的每个子区域中从预训练的深度卷积网络中生成多个空间上下文感知的表示。区域表示不仅描述了相应区域的局部特征，还描述了其多个空间上下文信息，使它们具有歧视性，对异常检测非常有益。利用这些描述性区域特征，我们设计了一个深层而有效的卷积自动编码器，并通过快速特征重建来检测图像中的异常区域。我们的方法简单而有效。它推进了几个基准数据集上最先进的性能，并显示出实际应用程序的巨大潜力。
Automatic detecting anomalous regions in images of objects or textures without priors of the anomalies is challenging, especially when the anomalies appear in very small areas of the images, making difficult-to-detect visual variations, such as defects on manufacturing products. This paper proposes an effective unsupervised anomaly segmentation approach that can detect and segment out the anomalies in small and confined regions of images. Concretely, we develop a multi-scale regional feature generator that can generate multiple spatial context-aware representations from pre-trained deep convolutional networks for every subregion of an image. The regional representations not only describe the local characteristics of corresponding regions but also encode their multiple spatial context information, making them discriminative and very beneficial for anomaly detection. Leveraging these descriptive regional features, we then design a deep yet efficient convolutional autoencoder and detect anomalous regions within images via fast feature reconstruction. Our method is simple yet effective and efficient. It advances the state-of-the-art performances on several benchmark datasets and shows great potential for real applications.
