In this paper, we address the problem of distillation-based class-incremental learning with a single head. A central theme of this task is to learn new classes that arrive in sequential phases over time while keeping the model's capability of recognizing seen classes with only limited memory for preserving seen data samples. Many regularization strategies have been proposed to mitigate the phenomenon of catastrophic forgetting. To understand better the essence of these regularizations, we introduce a feature-graph preservation perspective. Insights into their merits and faults motivate our weighted-Euclidean regularization for old knowledge preservation. We further propose rectified cosine normalization and show how it can work with binary cross-entropy to increase class separation for effective learning of new classes. Experimental results on both CIFAR-100 and ImageNet datasets demonstrate that our method outperforms the state-of-the-art approaches in reducing classification error, easing catastrophic forgetting, and encouraging evenly balanced accuracy over different classes. Our project page is at : https://github.com/yhchen12101/FGP-ICL.
翻译:在本文中,我们用一个头来探讨以蒸馏为主的阶级强化学习问题。 这项任务的中心主题是学习随着时间推移以相继阶段到达的新班级,同时保持模型在保存数据样本方面只保留有限记忆的识别被观察班级的能力。 已经提出了许多正规化战略来减轻灾难性遗忘现象。 为了更好地理解这些正规化的本质,我们引入了地貌保护观点。 观察它们的优点和缺点促使我们为旧的知识保存而进行加权-欧洲知识正规化。 我们进一步提出纠正共生法的正常化,并展示它如何与二进制交叉性合作,增加班级分离,以有效学习新班级。 CIFAR-100和图像网络数据集的实验结果显示,我们的方法在减少分类错误、减轻灾难性遗忘和鼓励不同班级的均衡准确性方面超过了最新方法。 我们的项目网页是: https://github.com/yhchen12101/FGP-ICL。