Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection
This addresses the critical problem of reliable OOD detection for deploying deep neural networks, representing an incremental improvement over existing methods.
The paper tackles out-of-distribution detection by introducing HEAT, a post-hoc method using hybrid energy-based models in feature space, which sets new state-of-the-art results on CIFAR-10/CIFAR-100 and ImageNet benchmarks.
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 in-distribution (ID) samples using hybrid energy-based models (EBM) in the feature space of a pre-trained backbone. HEAT complements prior density estimators of the ID density, e.g. parametric models like the Gaussian Mixture Model (GMM), 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 energy terms. Extensive experiments demonstrate the significance of the two contributions. HEAT sets new state-of-the-art OOD detection results on the CIFAR-10 / CIFAR-100 benchmark as well as on the large-scale Imagenet benchmark. The code is available at: https://github.com/MarcLafon/heatood.