English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Paper

LCC: Learning to Customize and Combine Neural Networks for Few-Shot Learning

MPS-Authors
/persons/resource/persons203020

Sun,  Qianru
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

/persons/resource/persons45383

Schiele,  Bernt
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)

arXiv:1904.08479.pdf
(Preprint), 2MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Liu, Y., Sun, Q., Liu, A.-A., Su, Y., Schiele, B., & Chua, T.-S. (2019). LCC: Learning to Customize and Combine Neural Networks for Few-Shot Learning. Retrieved from http://arxiv.org/abs/1904.08479.


Cite as: http://hdl.handle.net/21.11116/0000-0003-BAF9-3
Abstract
Meta-learning has been shown to be an effective strategy for few-shot learning. The key idea is to leverage a large number of similar few-shot tasks in order to meta-learn how to best initiate a (single) base-learner for novel few-shot tasks. While meta-learning how to initialize a base-learner has shown promising results, it is well known that hyperparameter settings such as the learning rate and the weighting of the regularization term are important to achieve best performance. We thus propose to also meta-learn these hyperparameters and in fact learn a time- and layer-varying scheme for learning a base-learner on novel tasks. Additionally, we propose to learn not only a single base-learner but an ensemble of several base-learners to obtain more robust results. While ensembles of learners have shown to improve performance in various settings, this is challenging for few-shot learning tasks due to the limited number of training samples. Therefore, our approach also aims to meta-learn how to effectively combine several base-learners. We conduct extensive experiments and report top performance for five-class few-shot recognition tasks on two challenging benchmarks: miniImageNet and Fewshot-CIFAR100 (FC100).