CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D Object Detection
This work addresses domain adaptation for 3D object detection in autonomous driving, which is an incremental improvement over existing methods.
The paper tackles the problem of poor generalization in LiDAR-based 3D object detection models across different domains by introducing CMDA, a novel unsupervised domain adaptation method that leverages visual semantic cues and adversarial self-training to close domain gaps, achieving state-of-the-art performance on benchmarks like nuScenes, Waymo, and KITTI.
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 the cross-modal Bird's Eye View (BEV) representations. Further, (ii) we also introduce a self-training-based learning strategy, wherein a model is adversarially trained to generate domain-invariant features, which disrupt the discrimination of whether a feature instance comes from a source or an unseen target domain. Overall, our CMDA framework guides the 3DOD model to generate highly informative and domain-adaptive features for novel data distributions. In our extensive experiments with large-scale benchmarks, such as nuScenes, Waymo, and KITTI, those mentioned above provide significant performance gains for UDA tasks, achieving state-of-the-art performance.