Class-incremental learning (CIL) suffers from the notorious dilemma between learning newly added classes and preserving previously learned class knowledge. That catastrophic forgetting issue could be mitigated by storing historical data for replay, which yet would cause memory overheads as well as imbalanced prediction updates. To address this dilemma, we propose to leverage "free" external unlabeled data querying in continual learning. We first present a CIL with Queried Unlabeled Data (CIL-QUD) scheme, where we only store a handful of past training samples as anchors and use them to query relevant unlabeled examples each time. Along with new and past stored data, the queried unlabeled are effectively utilized, through learning-without-forgetting (LwF) regularizers and class-balance training. Besides preserving model generalization over past and current tasks, we next study the problem of adversarial robustness for CIL-QUD. Inspired by the recent success of learning robust models with unlabeled data, we explore a new robustness-aware CIL setting, where the learned adversarial robustness has to resist forgetting and be transferred as new tasks come in continually. While existing options easily fail, we show queried unlabeled data can continue to benefit, and seamlessly extend CIL-QUD into its robustified versions, RCIL-QUD. Extensive experiments demonstrate that CIL-QUD achieves substantial accuracy gains on CIFAR-10 and CIFAR-100, compared to previous state-of-the-art CIL approaches. Moreover, RCIL-QUD establishes the first strong milestone for robustness-aware CIL. Codes are available in https://github.com/VITA-Group/CIL-QUD.
翻译:在学习新增加的班级和保存先前学到的班级知识之间,存在着臭名昭著的两难困境。这个灾难性的忘却问题可以通过储存历史数据进行重播来缓解,而历史数据却会导致记忆管理管理以及不平衡的预测更新。为了解决这一难题,我们提议利用“免费”外部无标签数据查询来不断学习。我们首先用查询无标签数据(CIL-QUD)来介绍CIL(CIL)计划,我们只储存少数过去的培训样本作为锚点,并每次都用它们来查询相关的未贴标签的例子。与新的和过去的存储数据一起,被查询的无标签问题可以被有效利用,通过学习不忘不忘的常规数据(LWF)正规化者和班级平衡培训。除了保留以往和当前任务的模型化外,我们下一步研究CIL-QUD(C-QUD)的对抗性强势强势问题。受最近学习强势模型的成功启发,我们探索新的稳健的CUD(C-IL)设置,我们所学的抗争健健健健健的Q(C-L-IL-IL-C-ILD-C-C-C-IL-C-C-IL-C-C-C-C-C-C-ILD-C-C-IL-C-C-C-C-C-IL-C-C-C-C-C-C-C-C-C-IL-C-C-C-C-C-C-C-C-C-IL-C-C-C-C-C-C-C-C-IL-C-C-C-C-C-C-IL-C-C-C-C-C-C-C-C-IL-C-C-C-C-C-IL-IL-C-C-C-C-C-IL-C-C-C-C-C-C-IL-C-IL-C-C-C-C-C-C-C-C-IL-IL-C-C-C-C-C-C-C-C-C-C-IL-IL-C-C-C-