CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D Object Detection

arXiv:2403.03721v1 Announce Type: new
Abstract: Recent LiDAR-based 3D Object Detection (3DOD) methods show promising results, but they often do not generalize well to target domains outside the source (or training) data distribution. To reduce such domain gaps and thus to make 3DOD models more generalizable, we introduce a novel unsupervised domain adaptation (UDA) method, called CMDA, which (i) leverages visual semantic cues from an image modality (i.e., camera images) as an effective semantic bridge to close the domain gap in …

3d object 3d object detection abstract adversarial arxiv cs.cv data detection distribution domain domains lidar modal novel object reduce results show training type