Meta-Learning for One-Shot Classification
- Title
- Meta-Learning for One-Shot Classification
- Authors
- 박민섭
- Date Issued
- 2018
- Publisher
- 포항공과대학교
- Abstract
- In this thesis, an ensemble method to improve one-shot classification was
proposed. Ensemble method in deep learning usually is done by combining dif
ferent initialization of prediction models with additional parameters as much as
the number of ensemble members, whereas our method ensemble from the end
points of the model in learning procedure without any additional parameters.
This method can be applied in one-shot learning training phase which dataset
is continuously being changed from episode to episode and end point has much
more variance than usual classification problem. From this way, some ensemble
members are better representing and classifying one-shot data, we find novel way
to ensemble which is inspired by meta recognition system; meta-classifier. Meta
classifier selects the best ensemble predictor and we achieve better performance
than existing method on miniImageNet and CIFAR dataset. Furthermore, we ex
perimented one-shot task with state-of-the-art base classifier and verify the best
performance of one-shot classification.
- URI
- http://postech.dcollection.net/common/orgView/200000008015
https://oasis.postech.ac.kr/handle/2014.oak/93570
- Article Type
- Thesis
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.