Out-of-Distribution Detection Using Neural Rendering Generative Models

by   Yujia Huang, et al.

Out-of-distribution (OoD) detection is a natural downstream task for deep generative models, due to their ability to learn the input probability distribution. There are mainly two classes of approaches for OoD detection using deep generative models, viz., based on likelihood measure and the reconstruction loss. However, both approaches are unable to carry out OoD detection effectively, especially when the OoD samples have smaller variance than the training samples. For instance, both flow based and VAE models assign higher likelihood to images from SVHN when trained on CIFAR-10 images. We use a recently proposed generative model known as neural rendering model (NRM) and derive metrics for OoD. We show that NRM unifies both approaches since it provides a likelihood estimate and also carries out reconstruction in each layer of the neural network. Among various measures, we found the joint likelihood of latent variables to be the most effective one for OoD detection. Our results show that when trained on CIFAR-10, lower likelihood (of latent variables) is assigned to SVHN images. Additionally, we show that this metric is consistent across other OoD datasets. To the best of our knowledge, this is the first work to show consistently lower likelihood for OoD data with smaller variance with deep generative models.


page 12

page 13

page 14


Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder

Deep probabilistic generative models enable modeling the likelihoods of ...

Deep Generative Models: Deterministic Prediction with an Application in Inverse Rendering

Deep generative models are stochastic neural networks capable of learnin...

SR-OOD: Out-of-Distribution Detection via Sample Repairing

It is widely reported that deep generative models can classify out-of-di...

Cyberattack Detection using Deep Generative Models with Variational Inference

Recent years have witnessed a rise in the frequency and intensity of cyb...

Topographic VAEs learn Equivariant Capsules

In this work we seek to bridge the concepts of topographic organization ...

Unsupervised Out-of-Distribution Detection with Batch Normalization

Likelihood from a generative model is a natural statistic for detecting ...

Scalable Font Reconstruction with Dual Latent Manifolds

We propose a deep generative model that performs typography analysis and...

Please sign up or login with your details

Forgot password? Click here to reset