论文标题
探测情境多样性以进行密集的分布检测
Probing Contextual Diversity for Dense Out-of-Distribution Detection
论文作者
论文摘要
在图像分类的背景下，检测到分布（OOD）样本最近已成为感兴趣的领域和积极研究，以及与不确定性估计的主题，与之密切相关。在本文中，我们探讨了OOD细分的任务，该任务的研究少于其分类，并提出了其他挑战。细分是一个密集的预测任务，每个像素的模型结果都取决于其周围环境。接收领域和对上下文的依赖在区分不同类别以及相应地发现OOD实体方面发挥了作用。我们介绍了Moose，这是一种有效的策略，旨在利用语义分割模型中表示的各种上下文级别，并表明，即使是多尺度表示的简单聚合，对OOD检测和不确定性估计的始终都会产生积极影响。
Detection of out-of-distribution (OoD) samples in the context of image classification has recently become an area of interest and active study, along with the topic of uncertainty estimation, to which it is closely related. In this paper we explore the task of OoD segmentation, which has been studied less than its classification counterpart and presents additional challenges. Segmentation is a dense prediction task for which the model's outcome for each pixel depends on its surroundings. The receptive field and the reliance on context play a role for distinguishing different classes and, correspondingly, for spotting OoD entities. We introduce MOoSe, an efficient strategy to leverage the various levels of context represented within semantic segmentation models and show that even a simple aggregation of multi-scale representations has consistently positive effects on OoD detection and uncertainty estimation.
