MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detection
This addresses the domain gap issue in 3D object detection for autonomous driving systems, but it is incremental as it builds on existing self-training and ensembling methods.
The paper tackles the problem of deploying 3D object detectors in unfamiliar domains, which causes a 70-90% drop in detection rate, by introducing MS3D++, a self-training framework that generates high-quality pseudo-labels to achieve state-of-the-art performance comparable to human-annotated labels on datasets like Waymo, nuScenes, and Lyft.
Deploying 3D detectors in unfamiliar domains has been demonstrated to result in a significant 70-90% drop in detection rate due to variations in lidar, geography, or weather from their training dataset. This domain gap leads to missing detections for densely observed objects, misaligned confidence scores, and increased high-confidence false positives, rendering the detector highly unreliable. To address this, we introduce MS3D++, a self-training framework for multi-source unsupervised domain adaptation in 3D object detection. MS3D++ generates high-quality pseudo-labels, allowing 3D detectors to achieve high performance on a range of lidar types, regardless of their density. Our approach effectively fuses predictions of an ensemble of multi-frame pre-trained detectors from different source domains to improve domain generalization. We subsequently refine predictions temporally to ensure temporal consistency in box localization and object classification. Furthermore, we present an in-depth study into the performance and idiosyncrasies of various 3D detector components in a cross-domain context, providing valuable insights for improved cross-domain detector ensembling. Experimental results on Waymo, nuScenes and Lyft demonstrate that detectors trained with MS3D++ pseudo-labels achieve state-of-the-art performance, comparable to training with human-annotated labels in Bird's Eye View (BEV) evaluation for both low and high density lidar. Code is available at https://github.com/darrenjkt/MS3D