我的新闻

祝贺团队小样本类增量学习的工作被CVPR20录用为Oral


2020-03-13

祝贺团队小样本类增量学习的文章被CVPR20录用为Oral (录取率稍后更新)

恭喜小语!

文章最终得分为两个strong accept和一个weak accept

 

题目:小样本类增量学习

Few-Shot Class-Incremental Learning. CVPR 2020 ORAL

作者:陶小语,洪晓鹏,常新远,董松林,魏星,龚怡宏

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

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 topological structure of the feature manifold formed by different classes. On this basis, we propose the TOpology-Preserving knowledge InCrementer (TOPIC) framework. TOPIC mitigates forgetting of old classes by stabilizing the topology of NG that preserves old knowledge, and improves the feature 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.