Open-set segmentation is often conceived by complementing closed-set classification with anomaly detection. Existing dense anomaly detectors operate either through generative modelling of regular training data or by discriminating with respect to negative training data. These two approaches optimize different objectives and therefore exhibit different failure modes. Consequently, we propose the first dense hybrid anomaly score that fuses generative and discriminative cues. The proposed score can be efficiently implemented by upgrading any semantic segmentation model with dense estimates of data likelihood and dataset posterior. Our design is a remarkably good fit for efficient inference on large images due to negligible computational overhead over the closed-set baseline. The resulting dense hybrid open-set models require negative training images that can be sampled from an auxiliary negative dataset, from a jointly trained generative model, or from a mixture of both sources. We evaluate our contributions on benchmarks for dense anomaly detection and open-set segmentation. The experiments reveal strong open-set performance in spite of negligible computational overhead.

翻译：开放集分割通常通过结合闭集分类与异常检测来实现。现有的密集异常检测器要么通过对正常训练数据进行生成式建模，要么通过区分负训练数据进行判别式分析。这两种方法优化目标不同，因此表现出不同的失败模式。为此，我们提出了首个密集混合异常评分，融合了生成式与判别式线索。该评分可通过为任意语义分割模型添加数据似然与数据集后验的密集估计来高效实现。我们的设计因对闭集基线仅增加可忽略的计算开销，特别适用于大尺寸图像的高效推理。由此产生的密集混合开放集模型需要负训练图像，这些图像可从辅助负数据集、联合训练的生成模型或两者的混合来源中采样。我们在密集异常检测与开放集分割的基准测试中评估了贡献。实验表明，尽管计算开销可忽略，但模型展示了强劲的开放集性能。