We explore the problem of Incremental Generalized Category Discovery (IGCD). This is a challenging category incremental learning setting where the goal is to develop models that can correctly categorize images from previously seen categories, in addition to discovering novel ones. Learning is performed over a series of time steps where the model obtains new labeled and unlabeled data, and discards old data, at each iteration. The difficulty of the problem is compounded in our generalized setting as the unlabeled data can contain images from categories that may or may not have been observed before. We present a new method for IGCD which combines non-parametric categorization with efficient image sampling to mitigate catastrophic forgetting. To quantify performance, we propose a new benchmark dataset named iNatIGCD that is motivated by a real-world fine-grained visual categorization task. In our experiments we outperform existing related methods

翻译：我们探索了增量广义类别发现（IGCD）问题。这是一个具有挑战性的类别增量学习场景，其目标是开发能够正确分类来自先前见过类别的图像，同时还能发现新类别的模型。学习过程在多个时间步骤上进行，模型在每个迭代中获取新的标注和未标注数据，并丢弃旧数据。在我们的广义设置中，问题的难度进一步增加，因为未标注数据可能包含来自之前见过或未见过的类别的图像。我们提出了一种用于IGCD的新方法，该方法结合了非参数化分类与高效图像采样，以减轻灾难性遗忘。为了量化性能，我们提出了一个新的基准数据集iNatIGCD，该数据集源于真实世界中的细粒度视觉分类任务。在我们的实验中，我们优于现有的相关方法。