Standard machine learning is unable to accommodate inputs which do not belong to the training distribution. The resulting models often give rise to confident incorrect predictions which may lead to devastating consequences. This problem is especially demanding in the context of dense prediction since input images may be only partially anomalous. Previous work has addressed dense out-of-distribution detection by discriminative training with respect to off-the-shelf negative datasets. However, real negative data are unlikely to cover all modes of the entire visual world. To this end, we extend this approach by generating synthetic negative patches along the border of the inlier manifold. We leverage a jointly trained normalizing flow due to coverage-oriented learning objective and the capability to generate samples at different resolutions. We detect anomalies according to a principled information-theoretic criterion which can be consistently applied through training and inference. The resulting models set the new state of the art on benchmarks for out-of-distribution detection in road-driving scenes and remote sensing imagery, in spite of minimal computational overhead.

翻译：标准机器学习难以处理不属于训练分布的输入数据，由此产生的模型常会给出置信度极高的错误预测，可能导致灾难性后果。这一问题在密集预测场景中尤为严峻，因为输入图像可能仅存在局部异常。已有研究通过利用现成的负样本数据集进行判别式训练来解决密集异常分布外检测问题，但真实负样本数据无法覆盖整个视觉世界的所有模式。为此，我们通过在流形边界上生成合成负样本块来拓展该方法。我们利用联合训练的归一化流模型，该模型具有覆盖导向的学习目标以及生成不同分辨率样本的能力。我们基于可统一应用于训练和推理阶段的信息论原则性准则进行异常检测。尽管计算开销极低，所得模型在道路驾驶场景与遥感图像的分布外检测基准测试中均达到了最新最优性能。