Optimization of Image Embeddings for Few Shot Learning

Arvind Srinivasan, Aprameya Bharadwaj, Manasa Sathyan, S. Natarajan

2021

Abstract

In this paper, we improve the image embeddings generated in the graph neural network solution for few shot learning. We propose alternate architectures for existing networks such as Inception-Net, U-Net, Attention U-Net, and Squeeze-Net to generate embeddings and increase the accuracy of the models. We improve the quality of embeddings created at the cost of the time taken to generate them. The proposed implementations outperform the existing state of the art methods for 1-shot and 5-shot learning on the Omniglot dataset. The experiments involved a testing set and training set which had no common classes between them. The results for 5-way and 10-way/20-way tests have been tabulated.

Paper Citation

in Harvard Style

Srinivasan A., Bharadwaj A., Sathyan M. and Natarajan S. (2021). Optimization of Image Embeddings for Few Shot Learning.In Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-486-2, pages 236-242. DOI: 10.5220/0010243202360242

in Bibtex Style

@conference{icpram21,
author={Arvind Srinivasan and Aprameya Bharadwaj and Manasa Sathyan and S. Natarajan},
title={Optimization of Image Embeddings for Few Shot Learning},
booktitle={Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2021},
pages={236-242},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010243202360242},
isbn={978-989-758-486-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Optimization of Image Embeddings for Few Shot Learning
SN - 978-989-758-486-2
AU - Srinivasan A.
AU - Bharadwaj A.
AU - Sathyan M.
AU - Natarajan S.
PY - 2021
SP - 236
EP - 242
DO - 10.5220/0010243202360242