Human beings learn and accumulate hierarchical knowledge over their lifetime. This knowledge is associated with previous concepts for consolidation and hierarchical construction. However, current incremental learning methods lack the ability to build a concept hierarchy by associating new concepts to old ones. A more realistic setting tackling this problem is referred to as Incremental Implicitly-Refined Classification (IIRC), which simulates the recognition process from coarse-grained categories to fine-grained categories. To overcome forgetting in this benchmark, we propose Hierarchy-Consistency Verification (HCV) as an enhancement to existing continual learning methods. Our method incrementally discovers the hierarchical relations between classes. We then show how this knowledge can be exploited during both training and inference. Experiments on three setups of varying difficulty demonstrate that our HCV module improves performance of existing continual learning methods under this IIRC setting by a large margin. Code is available in https://github.com/wangkai930418/HCV_IIRC.
翻译:人类在其一生中学习和积累等级知识。这种知识与先前的合并和等级结构概念有关。然而,目前的递增学习方法缺乏通过将新概念与旧概念挂钩来建立概念等级的能力。解决这一问题的更现实的设置被称为递增隐含精细分类(IIRC),它模拟了从粗皮类到细细细分类的识别过程。为了克服这一基准中的忘记,我们提议等级-一致性核查(HCV)作为现有持续学习方法的强化。我们的方法逐渐发现各班之间的等级关系。然后我们展示了如何在培训和推断中利用这种知识。对三种不同困难的组合进行的实验表明,我们的HCV模块大大地改进了在这种分类下的现有持续学习方法的绩效。代码见https://github.com/wangkai930418/HCV_IIRC。