Unsupervised domain adaptation (UDA) addresses the problem of distribution shift between the unlabeled target domain and labelled source domain. While the single target domain adaptation (STDA) is well studied in both 2D and 3D vision literature, 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 \emph{{\bf M}ixup {\bf Ens}emble {\bf A}verage} or {\bf \emph{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 extensive 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). We make the code publicly available \href{https://github.com/sinAshish/MEnsA_mtda}{here}\footnote{\url{https://github.com/sinAshish/MEnsA_mtda}}.

翻译：无监督域自适应（UDA）旨在解决未标注目标域与标注源域之间的分布偏移问题。尽管单目标域自适应（STDA）在二维和三维视觉文献中已有充分研究，但多目标域自适应（MTDA）在三维数据上的探索仍十分有限，尽管其在自动驾驶系统等需要适应不同地理和气候条件的实际应用中具有广泛需求。我们通过提出一种混合所有域特征表示并利用集成平均实现更优域自适应性能的方法，为三维点云数据建立了MTDA基线，该方法称为**混合集成平均（Mixup Ensemble Average，MEnsA）**。通过混合表示，我们使用域分类器在共享潜空间中更好地区分源域与目标域的特征表示。在具有挑战性的PointDA-10数据集上进行的大量实证验证表明，我们提出的简单方法在全部域迁移的平均性能上显著优于现有无监督STDA和MTDA方法（最高提升达17.10%和4.76%）。相关代码已开源，详见\href{https://github.com/sinAshish/MEnsA_mtda}{此处}\footnote{\url{https://github.com/sinAshish/MEnsA_mtda}}。