Discwise Active Learning for LiDAR Semantic Segmentation
| Autor: | Unal, Ozan, Dai, Dengxin, Unal, Ali Tamer, Van Gool, Luc |
|---|---|
| Rok vydání: | 2023 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | While LiDAR data acquisition is easy, labeling for semantic segmentation remains highly time consuming and must therefore be done selectively. Active learning (AL) provides a solution that can iteratively and intelligently label a dataset while retaining high performance and a low budget. In this work we explore AL for LiDAR semantic segmentation. As a human expert is a component of the pipeline, a practical framework must consider common labeling techniques such as sequential labeling that drastically improve annotation times. We therefore propose a discwise approach (DiAL), where in each iteration, we query the region a single frame covers on global coordinates, labeling all frames simultaneously. We then tackle the two major challenges that emerge with discwise AL. Firstly we devise a new acquisition function that takes 3D point density changes into consideration which arise due to location changes or ego-vehicle motion. Next we solve a mixed-integer linear program that provides a general solution to the selection of multiple frames while taking into consideration the possibilities of disc intersections. Finally we propose a semi-supervised learning approach to utilize all frames within our dataset and improve performance. Comment: Accepted at IEEE RA-L |
| Databáze: | arXiv |
| Externí odkaz: |
|