As AI agents are increasingly used in the real open world with unknowns or novelties, they need the ability to (1) recognize objects that (i) they have learned and (ii) detect items that they have not seen or learned before, and (2) learn the new items incrementally to become more and more knowledgeable and powerful. (1) is called novelty detection or out-of-distribution (OOD) detection and (2) is called class incremental learning (CIL), which is a setting of continual learning (CL). In existing research, OOD detection and CIL are regarded as two completely different problems. This paper theoretically proves that OOD detection actually is necessary for CIL. We first show that CIL can be decomposed into two sub-problems: within-task prediction (WP) and task-id prediction (TP). We then prove that TP is correlated with OOD detection. The key theoretical result is that regardless of whether WP and OOD detection (or TP) are defined explicitly or implicitly by a CIL algorithm, good WP and good OOD detection are necessary and sufficient conditions for good CIL, which unifies novelty or OOD detection and continual learning (CIL, in particular). A good CIL algorithm based on our theory can naturally be used in open world learning, which is able to perform both novelty/OOD detection and continual learning. Based on the theoretical result, new CIL methods are also designed, which outperform strong baselines in terms of CIL accuracy and its continual OOD detection by a large margin.

翻译：随着人工智能代理越来越多地被应用于存在未知或新事物的真实开放世界，它们需要具备以下能力：（1）识别（i）已学习过的对象，并（ii）检测之前未见或未学习过的项目；（2）增量式地学习新项目，以逐步变得更博学、更强大。能力（1）称为新颖性检测或分布外（OOD）检测，能力（2）称为类增量学习（CIL），这是持续学习（CL）的一种设定。在现有研究中，OOD检测与CIL被视为两个完全不同的问题。本文从理论上证明了OOD检测实际上对CIL是必要的。我们首先表明CIL可分解为两个子问题：任务内预测（WP）和任务ID预测（TP）。随后证明TP与OOD检测相关。关键的理论结果是：无论WP和OOD检测（或TP）是由CIL算法显式或隐式定义，良好的WP和良好的OOD检测是优质CIL的必要且充分条件，这统一了新颖性或OOD检测与持续学习（特别是CIL）。基于我们理论构建的良好CIL算法可自然地应用于开放世界学习，它能够同时执行新颖性/OOD检测和持续学习。基于该理论结果，我们还设计了新的CIL方法，在CIL准确率及其持续OOD检测方面大幅优于强基线方法。