HD-OOD3D: Supervised and Unsupervised Out-of-Distribution object detection in LiDAR data
This addresses a critical safety issue for autonomous vehicles by improving detection of unknown objects, but it appears incremental as it builds on existing two-stage approaches.
The paper tackles the problem of detecting out-of-distribution objects in LiDAR data for autonomous systems, showing that a two-stage method achieves more robust detection and highlighting issues with evaluation protocols and hyperparameter choices.
Autonomous systems rely on accurate 3D object detection from LiDAR data, yet most detectors are limited to a predefined set of known classes, making them vulnerable to unexpected out-of-distribution (OOD) objects. In this work, we present HD-OOD3D, a novel two-stage method for detecting unknown objects. We demonstrate the superiority of two-stage approaches over single-stage methods, achieving more robust detection of unknown objects while addressing key challenges in the evaluation protocol. Furthermore, we conduct an in-depth analysis of the standard evaluation protocol for OOD detection, revealing the critical impact of hyperparameter choices. To address the challenge of scaling the learning of unknown objects, we explore unsupervised training strategies to generate pseudo-labels for unknowns. Among the different approaches evaluated, our experiments show that top-5 auto-labelling offers more promising performance compared to simple resizing techniques.