A Meta-Learning Approach for Custom Model Training
원문 초록
Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large data sources to new tasks. In few-class, few-shot target task settings (i.e. when there are only a few classes and training examples available in the target task), meta-learning approaches that optimize for future task learning have outperformed the typical transfer approach of initializing model weights from a pre-trained starting point. But as we experimentally show, meta-learning algorithms that work well in the few-class setting do not generalize well in many-shot and many-class cases. In this paper, we propose a joint training approach that combines both transfer-learning and meta-learning. Benefiting from the advantages of each, our method obtains improved generalization performance on unseen target tasks in both few- and many-class and few- and many-shot scenarios.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
The Bayesian Approach to Continual Learning: An Overview
Acquiring and Adapting Priors for Novel Tasks via Neural Meta-Architectures
High-Order Deep Meta-Learning with Category-Theoretic Interpretation
Less is More: Undertraining Experts Improves Model Upcycling
The OCR Quest for Generalization: Learning to recognize low-resource alphabets with model editing
Cross-Domain Few-Shot Semantic Segmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.