Semantic segmentation models classify pixels into a set of known (``in-distribution'') visual classes. When deployed in an open world, the reliability of these models depends on their ability not only to classify in-distribution pixels but also to detect out-of-distribution (OoD) pixels. Historically, the poor OoD detection performance of these models has motivated the design of methods based on model re-training using synthetic training images that include OoD visual objects. Although successful, these re-trained methods have two issues: 1) their in-distribution segmentation accuracy may drop during re-training, and 2) their OoD detection accuracy does not generalise well to new contexts (e.g., country surroundings) outside the training set (e.g., city surroundings). In this paper, we mitigate these issues with: (i) a new residual pattern learning (RPL) module that assists the segmentation model to detect OoD pixels without affecting the inlier segmentation performance; and (ii) a novel context-robust contrastive learning (CoroCL) that enforces RPL to robustly detect OoD pixels among various contexts. Our approach improves by around 10\% FPR and 7\% AuPRC the previous state-of-the-art in Fishyscapes, Segment-Me-If-You-Can, and RoadAnomaly datasets. Our code is available at: https://github.com/yyliu01/RPL.

翻译：语义分割模型将像素分类到一组已知的（“分布内”）视觉类别中。当在开放世界中部署时，这些模型的可靠性不仅取决于其对分布内像素进行分类的能力，还取决于其检测分布外（OoD）像素的能力。历史上，这些模型较差的OoD检测性能促使人们设计基于模型重新训练的方法，这些方法使用包含OoD视觉对象的合成训练图像。尽管这些重新训练的方法取得了成功，但它们存在两个问题：1）在重新训练过程中，其分布内分割精度可能会下降；2）其OoD检测精度不能很好地泛化到训练集（如城市环境）之外的新场景（如乡村环境）。在本文中，我们通过以下方法缓解了这些问题：（i）一种新的残差模式学习（RPL）模块，该模块辅助分割模型检测OoD像素，同时不影响内点分割性能；（ii）一种新颖的上下文鲁棒对比学习（CoroCL），它强制RPL在各种上下文中稳健地检测OoD像素。我们的方法在Fishyscapes、Segment-Me-If-You-Can和RoadAnomaly数据集上将之前的先进水平提高了约10%的假阳性率（FPR）和7%的精确率-召回率曲线下面积（AuPRC）。我们的代码可在 https://github.com/yyliu01/RPL 获取。