Open-world Semantic Segmentation for LIDAR Point Clouds

TL;DR

This paper introduces an open-world semantic segmentation framework for LIDAR point clouds that can identify new classes and incrementally learn without forgetting, improving robustness for autonomous driving applications.

Contribution

It proposes the REAL framework that addresses open-set segmentation and incremental learning for LIDAR data, a novel approach in this domain.

Findings

Achieves state-of-the-art open-set segmentation performance on SemanticKITTI and nuScenes.

Effectively mitigates catastrophic forgetting during incremental learning.

Demonstrates robustness in real-world autonomous driving scenarios.

Abstract

Current methods for LIDAR semantic segmentation are not robust enough for real-world applications, e.g., autonomous driving, since it is closed-set and static. The closed-set assumption makes the network only able to output labels of trained classes, even for objects never seen before, while a static network cannot update its knowledge base according to what it has seen. Therefore, in this work, we propose the open-world semantic segmentation task for LIDAR point clouds, which aims to 1) identify both old and novel classes using open-set semantic segmentation, and 2) gradually incorporate novel objects into the existing knowledge base using incremental learning without forgetting old classes. For this purpose, we propose a REdundAncy cLassifier (REAL) framework to provide a general architecture for both the open-set semantic segmentation and incremental learning problems. The experimental results show that REAL can simultaneously achieves state-of-the-art performance in the open-set semantic segmentation task on the SemanticKITTI and nuScenes datasets, and alleviate the catastrophic forgetting problem with a large margin during incremental learning.