Recent semantic segmentation models accurately classify test-time examples that are similar to a training dataset distribution. However, their discriminative closed-set approach is not robust in practical data setups with distributional shifts and out-of-distribution (OOD) classes. As a result, the predicted probabilities can be very imprecise when used as confidence scores at test time. To address this, we propose a generative model for concurrent in-distribution misclassification (IDM) and OOD detection that relies on a normalizing flow framework. The proposed flow-based detector with an energy-based inputs (FlowEneDet) can extend previously deployed segmentation models without their time-consuming retraining. Our FlowEneDet results in a low-complexity architecture with marginal increase in the memory footprint. FlowEneDet achieves promising results on Cityscapes, Cityscapes-C, FishyScapes and SegmentMeIfYouCan benchmarks in IDM/OOD detection when applied to pretrained DeepLabV3+ and SegFormer semantic segmentation models.

翻译：近期语义分割模型能够准确分类与训练数据集分布相似的测试样本。然而，其基于判别式的闭集方法在面对分布偏移和分布外（OOD）类别的实际数据场景时缺乏鲁棒性。因此，在测试阶段使用预测概率作为置信度分数时可能极不精确。为解决该问题，我们提出了一种基于归一化流框架的生成式模型，用于同时进行分布内误分类（IDM）和OOD检测。所提出的基于能量输入的流式检测器（FlowEneDet）可扩展先前部署的分割模型，无需耗时重新训练。我们的FlowEneDet实现了低复杂度架构，仅带来内存占用的小幅增加。在应用于预训练的DeepLabV3+和SegFormer语义分割模型时，FlowEneDet在Cityscapes、Cityscapes-C、FishyScapes及SegmentMeIfYouCan基准测试的IDM/OOD检测任务中取得了显著成果。