Distributional Instance Segmentation: Modeling Uncertainty and High Confidence Predictions with Latent-MaskRCNN
This addresses the need for high-precision and reliable instance segmentation in robotic applications, such as industrial picking, by reducing errors in ambiguous scenes.
The paper tackles the problem of instance segmentation in robotic systems by modeling uncertainty over object masks to reduce critical errors, achieving a significant reduction in double pick errors on a real-world apparel-picking robot.
Object recognition and instance segmentation are fundamental skills in any robotic or autonomous system. Existing state-of-the-art methods are often unable to capture meaningful uncertainty in challenging or ambiguous scenes, and as such can cause critical errors in high-performance applications. In this paper, we explore a class of distributional instance segmentation models using latent codes that can model uncertainty over plausible hypotheses of object masks. For robotic picking applications, we propose a confidence mask method to achieve the high precision necessary in industrial use cases. We show that our method can significantly reduce critical errors in robotic systems, including our newly released dataset of ambiguous scenes in a robotic application. On a real-world apparel-picking robot, our method significantly reduces double pick errors while maintaining high performance.