Abstract
In the past few years, we have seen great progress in perception algorithms, particular through the use of deep learning. However, most existing approaches focus on a few categories of interest, which represent only a small fraction of the potential categories that robots need to handle in the real-world. Thus, identifying objects from unknown classes remains a challenging yet crucial task. In this paper, we develop a novel open-set instance segmentation algorithm for point clouds which can segment objects from both known and unknown classes in a holistic way. Our method uses a deep convolutional neural network to project points into a category-agnostic embedding space in which they can be clustered into instances irrespective of their semantics. Experiments on two large-scale self-driving datasets validate the effectiveness of our proposed method.
Original language | English (US) |
---|---|
Pages (from-to) | 384-393 |
Number of pages | 10 |
Journal | Proceedings of Machine Learning Research |
Volume | 100 |
State | Published - 2019 |
Event | 3rd Conference on Robot Learning, CoRL 2019 - Osaka, Japan Duration: Oct 30 2019 → Nov 1 2019 |
Keywords
- Autonomous Driving
- Instance Segmentation
- Open-Set Perception
ASJC Scopus subject areas
- Artificial Intelligence
- Software
- Control and Systems Engineering
- Statistics and Probability