Journal
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
Volume 59, Issue -, Pages 563-573Publisher
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.jvcir.2019.02.006
Keywords
Few-shot learning; Principal characteristic; Mixture loss function; Embedding network; Fine-tuning
Funding
- National Natural Science Foundation of China [61672202]
Ask authors/readers for more resources
Few-shot learning aims to build a classifier that recognizes unseen new classes given only a few samples of them. Previous studies like prototypical networks utilized the mean of embedded support vectors to represent the prototype that is the representation of class and yield satisfactory results. However, the importance of these different embedded support vectors is not studied yet, which are valuable factors that could be used to push the limit of the few-shot learning. We propose a principal characteristic network that exploits the principal characteristic to better express prototype, computed by distributing weights based on embedded vectors' different importance. The high-level abstract embedded vectors are extracted from our eResNet embedding network. In addition, we proposed a mixture loss function, which enlarges the inter-class distance in the embedding space for accurate classification. Extensive experimental results demonstrate that our network achieves state-of-the-art results on the Omniglot, minilmageNet and Cifar100 datasets. (C) 2019 Elsevier Inc. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available