Version 1
: Received: 2 March 2020 / Approved: 3 March 2020 / Online: 3 March 2020 (11:09:53 CET)
How to cite:
Dong, F.; Li, F. Multi-Stage Meta-Learning for Few-Shot with Lie Group Network Constraint. Preprints2020, 2020030035. https://doi.org/10.20944/preprints202003.0035.v1
Dong, F.; Li, F. Multi-Stage Meta-Learning for Few-Shot with Lie Group Network Constraint. Preprints 2020, 2020030035. https://doi.org/10.20944/preprints202003.0035.v1
Dong, F.; Li, F. Multi-Stage Meta-Learning for Few-Shot with Lie Group Network Constraint. Preprints2020, 2020030035. https://doi.org/10.20944/preprints202003.0035.v1
APA Style
Dong, F., & Li, F. (2020). Multi-Stage Meta-Learning for Few-Shot with Lie Group Network Constraint. Preprints. https://doi.org/10.20944/preprints202003.0035.v1
Chicago/Turabian Style
Dong, F. and Fanzhang Li. 2020 "Multi-Stage Meta-Learning for Few-Shot with Lie Group Network Constraint" Preprints. https://doi.org/10.20944/preprints202003.0035.v1
Abstract
Deep learning has achieved lots of successes in many fields, but when trainable sample are extremely limited, deep learning often under or overfitting to few samples. Meta-learning was proposed to solve difficulties in few-shot learning and fast adaptive areas. Meta-learner learns to remember some common knowledge by training on large scale tasks sampled from a certain data distribution to equip generalization when facing unseen new tasks. Due to the limitation of samples, most approaches only use shallow neural network to avoid overfitting and reduce the difficulty of training process, that causes the waste of many extra information when adapting to unseen tasks. Euclidean space-based gradient descent also make meta-learner's update inaccurate. These issues cause many meta-learning model hard to extract feature from samples and update network parameters. In this paper, we propose a novel method by using multi-stage joint training approach to post the bottleneck during adapting process. To accelerate adapt procedure, we also constraint network to Stiefel manifold, thus meta-learner could perform more stable gradient descent in limited steps. Experiment on mini-ImageNet shows that our method reaches better accuracy under 5-way 1-shot and 5-way 5-shot conditions.
Keywords
meta-learning; lie group; machine learning; deep learning; convolutional neural network
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.