25 citations · 33 across the 5 of their papers we have counts for
5 papers
Speech Tokenizer is Key to Consistent Representation
Wonjin Jung, Sungil Kang, Dong-Yeon Cho
Speech tokenization is crucial in digital speech processing, converting continuous speech signals into discrete units for various computational tasks. This paper introduces a novel…
Sample-based Regularization: A Transfer Learning Strategy Toward Better Generalization
Yunho Jeon, Yongseok Choi, Jaesun Park +3
Training a deep neural network with a small amount of data is a challenging problem as it is vulnerable to overfitting. However, one of the practical difficulties that we often fac…
Domain-Agnostic Few-Shot Classification by Learning Disparate Modulators
Yongseok Choi, Junyoung Park, Subin Yi +1
Although few-shot learning research has advanced rapidly with the help of meta-learning, its practical usefulness is still limited because most of them assumed that all meta-traini…
Discriminative Few-Shot Learning Based on Directional Statistics
Junyoung Park, Subin Yi, Yongseok Choi +2
Metric-based few-shot learning methods try to overcome the difficulty due to the lack of training examples by learning embedding to make comparison easy. We propose a novel algorit…
Meta Continual Learning
Risto Vuorio, Dong-Yeon Cho, Daejoong Kim +1
Using neural networks in practical settings would benefit from the ability of the networks to learn new tasks throughout their lifetimes without forgetting the previous tasks. This…