This paper is concerned with deep generative models (DGMs) for unsupervised out-of-distribution (OOD) detection. In particular, we focus on vanilla Variational Autoencoders (VAE) that use a standard normal prior distribution for the latent variables. These models have a smaller model size, enabling faster training and inference, making them well-suited for resource-limited applications compared to more complex DGMs. We propose a novel OOD score called Error Reduction (ER) specifically designed for vanilla VAE. ER incorporate the idea of reconstructing image inputs from their lossy counterparts and takes into account the Kolmogorov complexity of the images. Experimental results on diverse datasets demonstrate the superiority of our approach over baseline methods. Our code is available at: https://github.com/ZJLAB-AMMI/VAE4OOD.

翻译：本文关注用于无监督分布外（OOD）检测的深度生成模型（DGM）。特别地，我们聚焦于采用标准正态先验分布作为隐变量的原始变分自编码器（VAE）。与更复杂的DGM相比，这些模型具有更小的模型体积，支持更快的训练与推理速度，从而更适用于资源受限的应用场景。我们提出了一种名为误差缩减（ER）的新型OOD评分，专为原始VAE设计。ER将图像输入从其有损版本中重建的思路融入其中，并考虑了图像的Kolmogorov复杂度。在多个数据集上的实验结果表明，我们的方法优于基线方法。我们的代码已开源：https://github.com/ZJLAB-AMMI/VAE4OOD。