分布式实例分割：用潜在的 MaskRCNN 模型建模不确定性和高置信度预测（英文版）

英文标题：Distributional Instance Segmentation: Modeling Uncertainty and High Confidence Predictions with Latent-MaskRCNN中文摘要：本文提出一种基于概率分布的实例分割方法，利用潜在编码来建模物体掩膜的可能假设，从而降低机器人应用中的临界错误率。在实际服装拣选机器人上，该方法成功降低了错误率并提高了性能。英文摘要：Object recognition and instance segmentation are fundamental skills in anyrobotic or autonomous system. Existing state-of-the-art methods are oftenunable to capture meaningful uncertainty in challenging or ambiguous scenes,and as such can cause critical errors in high-performance applic