Different from human nature, it is still common practice today for vision tasks to train deep learning models only initially and on fixed datasets. A variety of approaches have recently addressed handling continual data streams. However, extending these methods to manage out-of-distribution (OOD) scenarios has not effectively been investigated. On the other hand, it has recently been shown that non-continual neural mesh models exhibit strong performance in generalizing to such OOD scenarios. To leverage this decisive property in a continual learning setting, we propose incremental neural mesh models that can be extended with new meshes over time. In addition, we present a latent space initialization strategy that enables us to allocate feature space for future unseen classes in advance and a positional regularization term that forces the features of the different classes to consistently stay in respective latent space regions. We demonstrate the effectiveness of our method through extensive experiments on the Pascal3D and ObjectNet3D datasets and show that our approach outperforms the baselines for classification by $2-6\%$ in the in-domain and by $6-50\%$ in the OOD setting. Our work also presents the first incremental learning approach for pose estimation. Our code and model can be found at https://github.com/Fischer-Tom/iNeMo.

翻译：与人类学习特性不同，当前视觉任务中仍普遍采用仅在初始阶段基于固定数据集训练深度学习模型的范式。近期已有多种方法致力于处理连续数据流，然而将这些方法扩展至处理分布外（OOD）场景的研究尚未取得实质性进展。另一方面，最新研究表明非连续神经网格模型在泛化至此类OOD场景时表现出卓越性能。为在持续学习环境中利用这一关键特性，本文提出可随时间推移扩展新网格的增量神经网格模型。此外，我们提出一种潜在空间初始化策略，能够预先为未来未见类别分配特征空间；同时引入位置正则化项，强制不同类别的特征持续驻留在各自对应的潜在空间区域。通过在Pascal3D和ObjectNet3D数据集上的大量实验，我们验证了方法的有效性：在域内分类任务中性能超越基线$2-6\%$，在OOD场景下提升幅度达$6-50\%$。本工作还首次提出了面向姿态估计任务的增量学习方法。代码与模型已开源：https://github.com/Fischer-Tom/iNeMo。