Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Open-world Semantic Segmentation for LIDAR Point Clouds

About

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.

Jun Cen, Peng Yun, Shiwei Zhang, Junhao Cai, Di Luan, Michael Yu Wang, Ming Liu, Mingqian Tang• 2022

Related benchmarks

TaskDatasetResultRank
Semantic segmentationS3DIS
mIoU70.4
88
Semantic segmentationScanNet V2
mIoU64.9
54
3D Incremental Semantic SegmentationS3DIS
mIoU68.9
7
Showing 3 of 3 rows

Other info

Follow for update