Curriculum-Based Meta-learning

By Ji Zhang, Jingkuan Song, Yazhou Yao, Lianli Gao. 2021

28 citations recorded by the source corpus.

Meta-learning offers an effective solution to learn new concepts with scarce supervision through an episodic training scheme: a series of target-like tasks sampled from base classes are sequentially fed into a meta-learner to extract common knowledge across tasks, which can facilitate the quick acquisition of task-specific knowledge of the target task with few samples. Despite its noticeable improvements, the episodic training strategy samples tasks randomly and uniformly, without considering their hardness and quality, which may not progressively improve the meta-leaner's generalization ability. In this paper, we present a Curriculum-Based Meta-learning (CubMeta) method to train the meta-learner using tasks from easy to hard. Specifically, the framework of CubMeta is in a progressive way, and in each step, we design a module named BrotherNet to establish harder tasks and an effective learning scheme for obtaining an ensemble of stronger meta-learners. In this way, the meta-learner's generalization ability can be progressively improved, and better performance can be obtained even with fewer training tasks. We evaluate our method for few-shot classification on two benchmarks - mini-ImageNet and tiered-ImageNet, where it achieves consistent performance improvements on various meta-learning paradigms.

Subfields: Artificial Intelligence, 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

1. Lianli Gao
2. Ji Zhang
3. Hengtao Shen
4. Cheng Chen
5. Jingkuan Song
6. Ye Liu

In Computer Vision and Pattern Recognition

1. Lianli Gao
2. Jingkuan Song
3. Ji Zhang
4. Hengtao Shen
5. Cheng Chen
6. Ye Liu
7. Shiv Ram Dubey
8. Dacheng Tao

Citations in the corpus

• Class Gradient Projection For Continual Learning (2022, background): “Although the modern deep learning network (DNN) has shown good performance on the task at hand [5, 12, 24, 41, 46, 47], they always violently forget the previous knowledge when they learn new tasks.”
• Progressive Meta-Learning With Curriculum (2022, methodology): “An earlier version of this paper (CubMeta) was presented at the 2021 ACM Multimedia [1] [DOI: 10.”