分类学类增量学习
Taxonomic Class Incremental Learning
AI总结：
本文提出分类学类增量学习（TCIL）问题，通过基于分类树的参数继承方案实现知识从祖先类向后代类的增量迁移，并在CIFAR-100和ImageNet-100上超越现有SOTA方法。
摘要：
持续学习问题近年来受到越来越多的关注。然而，很少有工作质疑目前常用的基于随机类别任务课程的学习设置。这与人类持续学习存在显著差异，因为人类持续学习是由分类学课程引导的。在本工作中，我们提出了分类学类增量学习（TCIL）问题。在TCIL中，任务序列基于分类学类别树进行组织。我们将现有的类增量学习（CIL）和分类学学习方法统一为参数继承方案，并为TCIL学习引入一种新的参数继承方案。这使得知识能够通过参数继承从类分类法中的祖先类增量地迁移到后代类。在CIFAR-100和ImageNet-100上的实验表明了所提出的TCIL方法的有效性，其在CIFAR-100上的最终准确率比现有最先进（SOTA）方法高出2%，在ImageNet-100上高出3%。
英文摘要：
The problem of continual learning has attracted rising attention in recent years. However, few works have questioned the commonly used learning setup, based on a task curriculum of random class. This differs significantly from human continual learning, which is guided by taxonomic curricula. In this work, we propose the Taxonomic Class Incremental Learning (TCIL) problem. In TCIL, the task sequence is organized based on a taxonomic class tree. We unify existing approaches to CIL and taxonomic learning as parameter inheritance schemes and introduce a new such scheme for the TCIL learning. This enables the incremental transfer of knowledge from ancestor to descendant class of a class taxonomy through parameter inheritance. Experiments on CIFAR-100 and ImageNet-100 show the effectiveness of the proposed TCIL method, which outperforms existing SOTA methods by 2% in terms of final accuracy on CIFAR-100 and 3% on ImageNet-100.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
