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.

翻译：外分布（OOD）检测是深度神经网络部署的关键需求。本文提出HEAT模型，这是一种新的后验OOD检测方法，在预训练骨干网络的特征空间中利用混合能量模型（EBM）估计内分布（ID）样本的密度。HEAT补充了现有的ID密度先验估计器（如高斯混合模型等参数化模型），从而提供准确且鲁棒的密度估计。第二项贡献在于利用EBM框架实现统一的密度估计并组合多个能量项。大量实验证明了这两项贡献的重要性。HEAT在CIFAR-10 / CIFAR-100基准测试以及大规模ImageNet基准测试上均取得了OOD检测的最新最优结果。代码已开源：https://github.com/MarcLafon/heatood。