[3N3-IS-2e] Machine learning (5/5)

[3N3-IS-2e-04] A study on the effect of regularization for weight imprinting

〇Paulino Cristovao^1,2, Hidemoto Nakada^2,1, Yusuke Tanimura^2,1, Hideki Asoh² (1. University of Tsukuba, 2. The National Institute of Advanced Industrial Science and Technology)

Keywords:Weight imprinting, Latent representation, Few Shot learning, Deep Learning

We investigate the Few Shot Learning based on the weight imprinting technique. The performance of imprinted weights deeply depends on the quality of the representation the encoder creates. However, it is known that the extracted representation quality affects the performance of the imprinted model, it is not known what characteristics are required for weight imprinting. The representation leads to the highest classification accuracy for base classes might not be the best one for downstream imprinting tasks.
We are investigating how we can get a `better' representation in terms of WIP. Currently, we are focusing on regularization, model architecture, data augmentation, auxiliary dataset, and auxiliary tasks.