Open-Set LiDAR Panoptic Segmentation Guided by Uncertainty-Aware Learning

TL;DR

This paper introduces ULOPS, a novel open-set LiDAR panoptic segmentation framework that uses uncertainty-aware learning to detect and segment previously unseen object classes in autonomous driving environments.

Contribution

The work presents a new uncertainty-guided approach with Dirichlet-based evidential learning and novel loss functions for improved open-set segmentation performance.

Findings

ULOps outperforms existing methods on KITTI-360 and nuScenes datasets.

The approach effectively distinguishes known and unknown objects using uncertainty estimates.

Proposed loss functions enhance the model's ability to identify unknown instances.

Abstract

Autonomous vehicles that navigate in open-world environments may encounter previously unseen object classes. However, most existing LiDAR panoptic segmentation models rely on closed-set assumptions, failing to detect unknown object instances. In this work, we propose ULOPS, an uncertainty-guided open-set panoptic segmentation framework that leverages Dirichlet-based evidential learning to model predictive uncertainty. Our architecture incorporates separate decoders for semantic segmentation with uncertainty estimation, embedding with prototype association, and instance center prediction. During inference, we leverage uncertainty estimates to identify and segment unknown instances. To strengthen the model's ability to differentiate between known and unknown objects, we introduce three uncertainty-driven loss functions. Uniform Evidence Loss to encourage high uncertainty in unknown regions. Adaptive Uncertainty Separation Loss ensures a consistent difference in uncertainty estimates between known and unknown objects at a global scale. Contrastive Uncertainty Loss refines this separation at the fine-grained level. To evaluate open-set performance, we extend benchmark settings on KITTI-360 and introduce a new open-set evaluation for nuScenes. Extensive experiments demonstrate that ULOPS consistently outperforms existing open-set LiDAR panoptic segmentation methods.