Transfer learning is fundamental for addressing problems in settings with little training data. While several transfer learning approaches have been proposed in 3D, unfortunately, these solutions typically operate on an entire 3D object or even scene-level and thus, as we show, fail to generalize to new classes, such as deformable organic shapes. In addition, there is currently a lack of understanding of what makes pre-trained features transferable across significantly different 3D shape categories. In this paper, we make a step toward addressing these challenges. First, we analyze the link between feature locality and transferability in tasks involving deformable 3D objects, while also comparing different backbones and losses for local feature pre-training. We observe that with proper training, learned features can be useful in such tasks, but, crucially, only with an appropriate choice of the receptive field size. We then propose a differentiable method for optimizing the receptive field within 3D transfer learning. Jointly, this leads to the first learnable features that can successfully generalize to unseen classes of 3D shapes such as humans and animals. Our extensive experiments show that this approach leads to state-of-the-art results on several downstream tasks such as segmentation, shape correspondence, and classification. Our code is available at \url{https://github.com/pvnieo/vader}.

翻译：转移学习是解决在有限训练数据情况下问题的基础。尽管在3D场景中已经提出了几种转移学习方法，但不幸的是，这些解决方案通常在整个3D对象或甚至场景级别上进行操作，因此，正如我们展示的那样，无法推广到新的类别，例如可变形有机形状。此外，目前缺乏对预训练功能是否适用于显着不同的3D形状类别的了解。在本文中，我们迈出了解决这些挑战的一步。首先，我们分析了特征局部性和在涉及可变形3D对象的任务中可转移性之间的关联，同时比较了局部特征预训练的不同骨干和损失。我们观察到，通过恰当的训练，学到的特征在这些任务中是有用的，但是关键在于选择适当的感受野大小。然后，我们提出了一种可在3D转移学习中优化感受野的可微方法。综合来看，这导致了首次能够成功推广到看不见的类别的3D形状，例如人类和动物的可学习特征。我们广泛的实验表明，这种方法在分割、形状对应和分类等多个下游任务上都取得了最先进的结果。我们的代码可在 \url {https://github.com/pvnieo/vader} 上获得。