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: i. We propose VINIL, a self-incremental learner that can learn object instances sequentially, ii. We equip VINIL with self-supervision to by-pass the need for instance labelling, iii. We compare VINIL to label-supervised variants on two large-scale benchmarks, 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增量学习视觉对象实例（即自增量学习）。我们的学习器每次观察单个实例，随后该实例将从数据集中移除。增量实例学习颇具挑战性，因为较长的学习过程会加剧遗忘问题，且实例标注工作繁琐。我们通过三项创新克服这些挑战：一，提出VINIL——一种可顺序学习对象实例的自增量学习器；二，为VINIL配备自监督机制以规避实例标注需求；三，在两个大规模基准数据集上将VINIL与标签监督变体进行对比，结果表明VINIL显著提升精度的同时有效降低遗忘率。