In this paper, we learn to classify visual object instances, incrementally and via self-supervision (self-incremental). Our learner observes a single instance at a time, which is then discarded from the dataset. Incremental instance learning is challenging, since longer learning sessions exacerbate forgetfulness, and labeling instances is cumbersome. We overcome these challenges via three contributions: \textit{i).} We propose VINIL, a self-incremental learner that can learn object instances sequentially, \textit{ii).} We equip VINIL with self-supervision to by-pass the need for instance labelling, \textit{iii).} We compare VINIL to label-supervised variants on two large-scale benchmarks~\cite{core50,ilab20m}, and show that VINIL significantly improves accuracy while reducing forgetfulness.

翻译：本文研究如何通过自监督方式（自增量学习）逐步学习视觉对象实例的分类。我们的学习器每次仅观察单个实例，之后该实例将从数据集中移除。增量实例学习具有挑战性，因为较长的学习周期会加剧遗忘问题，且实例标注过程繁琐。我们通过三项贡献克服这些挑战：\textit{i)} 提出VINIL——一种能够顺序学习对象实例的自增量学习器；\textit{ii)} 为VINIL配备自监督机制，从而绕过实例标注需求；\textit{iii)} 在两个大规模基准数据集\cite{core50,ilab20m}上将VINIL与标签监督方法进行对比，结果表明VINIL在显著提升准确率的同时有效降低了遗忘程度。