论文标题
非独立班级学习的自我维持的表示
Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning
论文作者
论文摘要
当无法保存旧类样本时，非执行类知识学习是要识别旧类和新类。这是一项具有挑战性的任务，因为仅在新班级的监督下才能实现表示形式优化和功能保留。为了解决这个问题，我们提出了一种新颖的自我维持表示扩展方案。我们的计划包括一种结构重组策略，该策略融合了主要分支扩张和侧支更新以维护旧功能，以及一种主要分支蒸馏计划以传递不变知识。此外，提出了一种原型选择机制，以通过选择性地将新样品纳入蒸馏过程来增强旧类和新类之间的歧视。在三个基准上进行的广泛实验表明表现出明显的增量性能，表现分别超过了最先进的方法，分别以3％，3％和6％的利润率。
Non-exemplar class-incremental learning is to recognize both the old and new classes when old class samples cannot be saved. It is a challenging task since representation optimization and feature retention can only be achieved under supervision from new classes. To address this problem, we propose a novel self-sustaining representation expansion scheme. Our scheme consists of a structure reorganization strategy that fuses main-branch expansion and side-branch updating to maintain the old features, and a main-branch distillation scheme to transfer the invariant knowledge. Furthermore, a prototype selection mechanism is proposed to enhance the discrimination between the old and new classes by selectively incorporating new samples into the distillation process. Extensive experiments on three benchmarks demonstrate significant incremental performance, outperforming the state-of-the-art methods by a margin of 3%, 3% and 6%, respectively.
