论文标题
语义细分中的剩余图案学习，用于像素的分布式检测
Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation
论文作者
论文摘要
语义分割模型将像素分类为一组已知的（``分布''）视觉类别。当部署在开放世界中时，这些模型的可靠性不仅取决于它们不仅对分布像素进行分类的能力，还取决于检测分布外（OOD）像素的能力。从历史上看，这些模型的OOD检测性能差，可以使用包括OOD视觉对象的合成训练图像进行基于模型重新训练的方法设计。尽管成功，但这些重新训练的方法有两个问题：1）在重新训练期间，它们的分布分割精度可能会下降，而2）它们的OOD检测准确性并不能很好地推广到培训集外的新环境（例如国家环境）（例如，城市环境）之外的新环境（例如国家环境）。在本文中，我们通过以下方式缓解了这些问题：（i）一个新的残差模式学习（RPL）模块，该模块有助于分割模型检测OOD像素而不影响进口性分段性能； （ii）一种新颖的上下文对比度学习（COROCL），该学习强制执行RPL以在各种环境之间稳健地检测OOD像素。我们的方法提高了大约10 \％FPR和7 \％AUPRC，这是先前最新的FishyScapes，segment-me-if-if-if-if-you-can和Roadanomaly数据集。我们的代码可在以下网址提供：https：//github.com/yyliu01/rpl。
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.
