论文标题
使用矢量定量的变分自动编码器通过潜在空间恢复进行异常检测
Anomaly detection through latent space restoration using vector-quantized variational autoencoders
论文作者
论文摘要
我们提出了一种分布式检测方法，该方法使用矢量定量的变分自动编码器（VQ-VAE）结合了密度和基于恢复的方法。 VQ-VAE模型学会在分类潜在空间中编码图像。然后，使用自动回归（AR）模型对潜在代码的先前分布进行建模。我们发现，由AR模型估计的先验概率可用于无监督的异常检测，并可以估计样品和像素的异常得分。样本的得分定义为潜在变量的负模样，从阈值选择高度不可能的代码。此外，通过将不太可能的潜在代码替换为先前模型中的样本并解码为像素空间，将分布外图像恢复到分布图像中。生成的还原与原始图像之间的平均L1距离用作像素的异常得分。我们在情绪挑战数据集上测试了我们的方法，并报告了与VAE基于标准的基于重建的方法相比的更高精度。
We propose an out-of-distribution detection method that combines density and restoration-based approaches using Vector-Quantized Variational Auto-Encoders (VQ-VAEs). The VQ-VAE model learns to encode images in a categorical latent space. The prior distribution of latent codes is then modelled using an Auto-Regressive (AR) model. We found that the prior probability estimated by the AR model can be useful for unsupervised anomaly detection and enables the estimation of both sample and pixel-wise anomaly scores. The sample-wise score is defined as the negative log-likelihood of the latent variables above a threshold selecting highly unlikely codes. Additionally, out-of-distribution images are restored into in-distribution images by replacing unlikely latent codes with samples from the prior model and decoding to pixel space. The average L1 distance between generated restorations and original image is used as pixel-wise anomaly score. We tested our approach on the MOOD challenge datasets, and report higher accuracies compared to a standard reconstruction-based approach with VAEs.
