论文标题
DDR-ID：基于双重重建网络基于异常检测的图像分解
DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection
论文作者
论文摘要
图像异常检测（AD）检测的一个枢纽挑战是仅从正常的类培训图像中学习判别信息。大多数基于图像重建的AD方法都取决于重建误差的歧视能力。这是启发式的，因为图像重建是无监督的，而不包含正常类的信息。在本文中，我们提出了一种称为基于双重重建网络的图像分解（DDR-ID）的AD方法。通过共同优化三个损失的网络：一级损失，潜在空间限制损失和重建损失。训练后，DDR-ID可以分别将看不见的图像分别为正常类别和残留成分。计算两个异常得分以量化正常类潜在空间或重建图像空间中图像的异常程度。因此，可以通过阈值对异常得分进行异常检测。该实验表明，使用MNIST，CIFAR-10和内体数据集中，DDR-ID在图像异常检测中的多个相关基准测定方法以及使用GTSRB数据集的对抗性攻击检测。
One pivot challenge for image anomaly (AD) detection is to learn discriminative information only from normal class training images. Most image reconstruction based AD methods rely on the discriminative capability of reconstruction error. This is heuristic as image reconstruction is unsupervised without incorporating normal-class-specific information. In this paper, we propose an AD method called dual deep reconstruction networks based image decomposition (DDR-ID). The networks are trained by jointly optimizing for three losses: the one-class loss, the latent space constrain loss and the reconstruction loss. After training, DDR-ID can decompose an unseen image into its normal class and the residual components, respectively. Two anomaly scores are calculated to quantify the anomalous degree of the image in either normal class latent space or reconstruction image space. Thereby, anomaly detection can be performed via thresholding the anomaly score. The experiments demonstrate that DDR-ID outperforms multiple related benchmarking methods in image anomaly detection using MNIST, CIFAR-10 and Endosome datasets and adversarial attack detection using GTSRB dataset.
