Inconsistency-based Active Learning for LiDAR Object Detection
By: Esteban Rivera, Loic Stratil, Markus Lienkamp
Potential Business Impact:
Teaches self-driving cars with less data.
Deep learning models for object detection in autonomous driving have recently achieved impressive performance gains and are already being deployed in vehicles worldwide. However, current models require increasingly large datasets for training. Acquiring and labeling such data is costly, necessitating the development of new strategies to optimize this process. Active learning is a promising approach that has been extensively researched in the image domain. In our work, we extend this concept to the LiDAR domain by developing several inconsistency-based sample selection strategies and evaluate their effectiveness in various settings. Our results show that using a naive inconsistency approach based on the number of detected boxes, we achieve the same mAP as the random sampling strategy with 50% of the labeled data.
Similar Papers
Table Detection with Active Learning
CV and Pattern Recognition
Teaches computers to learn from fewer examples.
Label-efficient Single Photon Images Classification via Active Learning
Image and Video Processing
Teaches computers to understand tricky pictures faster.
Active Learning for Multi-class Image Classification
CV and Pattern Recognition
Teaches computers to learn with fewer pictures.