arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.10956cs.CVcs.LGstat.ML
收藏

Few-Shot类增量学习

Few-Shot Class-Incremental Learning

Xi’an Jiaotong University(西安交通大学);Peng Cheng Laboratory(鹏城实验室)

Xiaoyu Tao, Xiaopeng Hong, Xinyuan Chang, Songlin Dong, Xing Wei, Yihong Gong

摘要:

增量学习新类的能力对于开发真实世界的人工智能系统至关重要。在本文中,我们专注于一个具有挑战性的,但实际的Few-Shot类增量学习(FSCIL)问题。FSCIL要求CNN模型从很少的标记样本中增量学习新的类,而不会忘记以前学习的类。为了解决这个问题,我们使用神经气体(NG)网络来表示知识,该网络可以学习和保存由不同类形成的特征流形的拓扑结构。在此基础上,我们提出了拓扑保持知识增量(TOPIC)框架。TOPIC通过稳定NG的拓扑结构来减轻对旧类的遗忘,并通过增长NG并使其适应新的训练样本来改进对Few-Shot新类的表示学习。综合实验结果表明,我们提出的方法在CIFAR100,miniImageNet和CUB200数据集上的性能明显优于其他最先进的类增量学习方法。

英文摘要:

The ability to incrementally learn new classes is crucial to the development of real-world artificial intelligence systems. In this paper, we focus on a challenging but practical few-shot class-incremental learning (FSCIL) problem. FSCIL requires CNN models to incrementally learn new classes from very few labelled samples, without forgetting the previously learned ones. To address this problem, we represent the knowledge using a neural gas (NG) network, which can learn and preserve the topology of the feature manifold formed by different classes. On this basis, we propose the TOpology-Preserving knowledge InCrementer (TOPIC) framework. TOPIC mitigates the forgetting of the old classes by stabilizing NG's topology and improves the representation learning for few-shot new classes by growing and adapting NG to new training samples. Comprehensive experimental results demonstrate that our proposed method significantly outperforms other state-of-the-art class-incremental learning methods on CIFAR100, miniImageNet, and CUB200 datasets.

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。

↑