Meta Module Generation for Fast Few-Shot Incremental Learning

By Shudong Xie, Yiqun Li, Dongyun Lin, Tin Lay Nwe, Sheng Dong. 2019

7 citations recorded by the source corpus.

There are two challenging problems in applying standard Deep Neural Networks (DNNs) for incremental learning with a few examples: (i) DNNs do not perform well when little training data is available; (ii) DNNs suffer from catastrophic forgetting when used for incremental class learning. To simultaneously address both problems, we propose Meta Module Generation (MetaMG), a meta-learning method that enables a module generator to rapidly generate a category module from a few examples for a scalable classification network to recognize a new category. The old categories are not forgotten after new categories are added in. Comprehensive experiments conducted on 4 datasets show that our method is promising for fast incremental learning in few-shot setting. Further experiments on the miniImageNet dataset show that even it is not specially designed for the N-wayK-shot learning problem, MetaMG can sitll perform relatively well especially for 20-way K-shot setting.

Subfields: Artificial Intelligence, Cancer Research, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Continual Few-Shot Learning for Text Classification (2021, background): “Further, a few previous works have explored continual learning with few examples for computer vision tasks (Le et al., 2019; Xie et al., 2019; Douillard et al., 2020; Tao et al., 2020).”
A Survey on Few-Shot Class-Incremental Learning (2023, methodology): “Before the emergence of FSCIL, similar settings had been proposed in previous research, such as those presented by (Gidaris and Ko-modakis, 2018; Qi et al., 2018; Xie et al., 2019; Yoon et al., 2020).”