A Benchmark for Out of Distribution Detection in Point Cloud 3D Semantic Segmentation
This work addresses safety-critical applications like autonomous driving by providing a benchmark for OOD detection in point cloud data, though it is incremental as it adapts existing methods to a new domain.
The authors tackled the lack of benchmarks for out-of-distribution (OOD) detection in 3D semantic segmentation by proposing two datasets for LiDAR inputs, finding that Deep Ensembles outperform Flipout models with higher AUROC scores.
Safety-critical applications like autonomous driving use Deep Neural Networks (DNNs) for object detection and segmentation. The DNNs fail to predict when they observe an Out-of-Distribution (OOD) input leading to catastrophic consequences. Existing OOD detection methods were extensively studied for image inputs but have not been explored much for LiDAR inputs. So in this study, we proposed two datasets for benchmarking OOD detection in 3D semantic segmentation. We used Maximum Softmax Probability and Entropy scores generated using Deep Ensembles and Flipout versions of RandLA-Net as OOD scores. We observed that Deep Ensembles out perform Flipout model in OOD detection with greater AUROC scores for both datasets.