Poster: Feature-adaptive Re-MAML optimised for the input data set
Kaho Sunata, Taiga Kume, Jin Nakazawa, T. Okoshi · 2024
Deep learning models need a lot of labeled data, which is costly and time-consuming to collect. A method that learns a common knowledge (meta-knowledge) from similar tasks to train new tasks efficiently with fewer data is effective. We propose "Feature-adaptive Re-MAML" (FARe-MAML), a novel method for acquiring the most optimal learning method, taking into account the features of the new training data.