Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection

Out-of-distribution (OOD) detection is a critical requirement for the deployment of deep neural networks. This paper introduces the HEAT model, a new post-hoc OOD detection method estimating the density of <PRE_TAG><PRE_TAG>in-distribution (ID)</POST_TAG></POST_TAG> samples using <PRE_TAG><PRE_TAG>hybrid <PRE_TAG>energy-based models (EBM)</POST_TAG></POST_TAG></POST_TAG> in the <PRE_TAG>feature space</POST_TAG> of a <PRE_TAG>pre-trained backbone</POST_TAG>. HEAT complements prior density estimators of the ID density, e.g. parametric models like the <PRE_TAG>Gaussian Mixture Model (GMM)</POST_TAG>, to provide an accurate yet robust density estimation. A second contribution is to leverage the EBM framework to provide a unified density estimation and to compose several <PRE_TAG>energy terms</POST_TAG>. Extensive experiments demonstrate the significance of the two contributions. HEAT sets new state-of-the-art OOD detection results on the CIFAR-10 / <PRE_TAG>CIFAR-100</POST_TAG> benchmark as well as on the large-scale Imagenet benchmark. The code is available at: https://github.com/MarcLafon/heatood.