Plasticity and stability are needed in class-incremental learning in order to learn from new data while preserving past knowledge. Due to catastrophic forgetting, finding a compromise between these two properties is particularly challenging when no memory buffer is available. Mainstream methods need to store two deep models since they integrate new classes using fine tuning with knowledge distillation from the previous incremental state. We propose a method which has similar number of parameters but distributes them differently in order to find a better balance between plasticity and stability. Following an approach already deployed by transfer-based incremental methods, we freeze the feature extractor after the initial state. Classes in the oldest incremental states are trained with this frozen extractor to ensure stability. Recent classes are predicted using partially fine-tuned models in order to introduce plasticity. Our proposed plasticity layer can be incorporated to any transfer-based method designed for memory-free incremental learning, and we apply it to two such methods. Evaluation is done with three large-scale datasets. Results show that performance gains are obtained in all tested configurations compared to existing methods.
翻译:为了在保存过去知识的同时从新数据中学习,在课堂强化学习中需要可塑性和稳定性,以便从新数据中学习,同时保留过去的知识。由于灾难性的遗忘,在没有记忆缓冲的情况下,找到这两个属性之间的折中特别具有挑战性。主流方法需要存储两个深层模型,因为这两个模型使用与先前增量状态的知识蒸馏法的微调和知识蒸馏法合并新班级。我们建议采用一个参数数目相似的方法,但为在可塑性和稳定性之间找到更好的平衡而以不同的方式分配这些参数。在最初采用基于转移的增量法后,我们冻结了地物提取器。在最老的增量状态中,对各个类别进行了冷冻提取器的培训,以确保稳定性。预计最近的班将使用部分微调模型来引入塑料性。我们提议的塑料层可以纳入任何为无记忆增量学习而设计的基于转移的方法,我们将其应用于两种方法。通过三个大型数据集进行评估。结果显示,所有测试的配置与现有方法相比都取得了绩效收益。