MEnsA: Mix-up Ensemble Average for Unsupervised Multi Target Domain Adaptation on 3D Point Clouds
This addresses domain adaptation for 3D point clouds in applications like autonomous driving across varied conditions, but it is incremental as it builds on existing UDA methods with a novel ensemble approach.
The paper tackled unsupervised multi-target domain adaptation for 3D point clouds by proposing MEnsA, which mixes feature representations across domains and uses a domain classifier, achieving improvements of up to 17.10% and 4.76% over previous methods on the PointDA-10 dataset.
Unsupervised domain adaptation (UDA) addresses the problem of distribution shift between the unlabelled target domain and labelled source domain. While the single target domain adaptation (STDA) is well studied in the literature for both 2D and 3D vision tasks, multi-target domain adaptation (MTDA) is barely explored for 3D data despite its wide real-world applications such as autonomous driving systems for various geographical and climatic conditions. We establish an MTDA baseline for 3D point cloud data by proposing to mix the feature representations from all domains together to achieve better domain adaptation performance by an ensemble average, which we call Mixup Ensemble Average or MEnsA. With the mixed representation, we use a domain classifier to improve at distinguishing the feature representations of source domain from those of target domains in a shared latent space. In empirical validations on the challenging PointDA-10 dataset, we showcase a clear benefit of our simple method over previous unsupervised STDA and MTDA methods by large margins (up to 17.10% and 4.76% on averaged over all domain shifts).