LiON: Learning Point-wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic Data
This addresses the challenge of outlier detection in LiDAR data for autonomous driving perception, representing an incremental improvement over heuristic methods.
The paper tackles the problem of identifying outlier points in LiDAR point clouds for autonomous driving by introducing a selective classification approach that learns point-wise abstaining penalties, achieving state-of-the-art results on SemanticKITTI and nuScenes benchmarks.
LiDAR-based semantic scene understanding is an important module in the modern autonomous driving perception stack. However, identifying outlier points in a LiDAR point cloud is challenging as LiDAR point clouds lack semantically-rich information. While former SOTA methods adopt heuristic architectures, we revisit this problem from the perspective of Selective Classification, which introduces a selective function into the standard closed-set classification setup. Our solution is built upon the basic idea of abstaining from choosing any inlier categories but learns a point-wise abstaining penalty with a margin-based loss. Apart from learning paradigms, synthesizing outliers to approximate unlimited real outliers is also critical, so we propose a strong synthesis pipeline that generates outliers originated from various factors: object categories, sampling patterns and sizes. We demonstrate that learning different abstaining penalties, apart from point-wise penalty, for different types of (synthesized) outliers can further improve the performance. We benchmark our method on SemanticKITTI and nuScenes and achieve SOTA results. Codes are available at https://github.com/Daniellli/LiON/.