We propose a novel class incremental learning approach by incorporating a feature augmentation technique motivated by adversarial attacks. We employ a classifier learned in the past to complement training examples rather than simply play a role as a teacher for knowledge distillation towards subsequent models. The proposed approach has a unique perspective to utilize the previous knowledge in class incremental learning since it augments features of arbitrary target classes using examples in other classes via adversarial attacks on a previously learned classifier. By allowing the cross-class feature augmentations, each class in the old tasks conveniently populates samples in the feature space, which alleviates the collapse of the decision boundaries caused by sample deficiency for the previous tasks, especially when the number of stored exemplars is small. This idea can be easily incorporated into existing class incremental learning algorithms without any architecture modification. Extensive experiments on the standard benchmarks show that our method consistently outperforms existing class incremental learning methods by significant margins in various scenarios, especially under an environment with an extremely limited memory budget.

翻译：我们提出一种新颖的类别增量学习方法，该方法融合了受对抗攻击启发的特征增强技术。我们利用过去学习到的分类器来补充训练样本，而非仅作为知识蒸馏的教师模型作用于后续模型。该方法在类别增量学习中具有独特视角：通过对抗攻击先前学习的分类器，利用其他类别的样本来增强任意目标类别的特征。通过允许跨类特征增强，旧任务中的每个类别能够在特征空间中便捷地生成样本，从而缓解因样本不足（尤其是存储样本数量较少时）导致的旧任务决策边界崩溃问题。该思想无需修改架构即可轻松集成到现有类别增量学习算法中。在标准基准上的广泛实验表明，我们的方法在各种场景下均显著优于现有类别增量学习方法，尤其在内存预算极度受限的环境中表现突出。