Open-world Semantic Segmentation for LIDAR Point Clouds

07/04/2022
by   Jun Cen, et al.
0

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.

READ FULL TEXT

page 1

page 3

page 4

page 5

page 7

page 8

page 13

page 15

research
08/10/2021

Deep Metric Learning for Open World Semantic Segmentation

Classical close-set semantic segmentation networks have limited ability ...
research
05/12/2020

Class-Incremental Learning for Semantic Segmentation Re-Using Neither Old Data Nor Old Labels

While neural networks trained for semantic segmentation are essential fo...
research
02/17/2023

Few-shot 3D LiDAR Semantic Segmentation for Autonomous Driving

In autonomous driving, the novel objects and lack of annotations challen...
research
07/23/2019

Incremental Class Discovery for Semantic Segmentation with RGBD Sensing

This work addresses the task of open world semantic segmentation using R...
research
02/25/2020

3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation

LIDAR semantic segmentation, which assigns a semantic label to each 3D p...
research
03/01/2022

Understanding the Challenges When 3D Semantic Segmentation Faces Class Imbalanced and OOD Data

3D semantic segmentation (3DSS) is an essential process in the creation ...
research
06/25/2020

Fully Convolutional Open Set Segmentation

In semantic segmentation knowing about all existing classes is essential...

Please sign up or login with your details

Forgot password? Click here to reset