Human intelligence gradually accepts new information and accumulates knowledge throughout the lifespan. However, deep learning models suffer from a catastrophic forgetting phenomenon, where they forget previous knowledge when acquiring new information. Class-Incremental Learning aims to create an integrated model that balances plasticity and stability to overcome this challenge. In this paper, we propose a selective regularization method that accepts new knowledge while maintaining previous knowledge. We first introduce an asymmetric feature distillation method for old and new classes inspired by cognitive science, using the gradient of classification and knowledge distillation losses to determine whether to perform pattern completion or pattern separation. We also propose a method to selectively interpolate the weight of the previous model for a balance between stability and plasticity, and we adjust whether to transfer through model confidence to ensure the performance of the previous class and enable exploratory learning. We validate the effectiveness of the proposed method, which surpasses the performance of existing methods through extensive experimental protocols using CIFAR-100, ImageNet-Subset, and ImageNet-Full.

翻译：人类智能在整个生命周期中逐步接收新信息并积累知识。然而，深度学习模型存在灾难性遗忘问题，即在获取新信息时会遗忘先前知识。类别增量学习旨在构建一个兼具可塑性与稳定性的综合模型以应对这一挑战。本文提出一种选择性正则化方法，可在维持已有知识的同时接纳新知识。首先，受认知科学启发，我们针对新旧类别引入非对称特征蒸馏方法，利用分类损失与知识蒸馏损失的梯度决定执行模式完成还是模式分离。其次，我们提出一种方法，通过选择性插值先前模型的权重以平衡稳定性与可塑性，并依据模型置信度调整知识迁移策略，从而保障先前类别性能并支持探索性学习。通过基于CIFAR-100、ImageNet子集及ImageNet完整数据集的大量实验验证，本方法有效超越现有方法性能。