Prior-Knowledge and Attention-based Meta-Learning for Few-Shot Learning
This work improves few-shot learning for AI systems by integrating human-like cognitive processes, though it is incremental as it builds on existing meta-learning methods.
The paper tackles few-shot learning by introducing a meta-learning approach that incorporates prior-knowledge and attention mechanisms to reduce the meta-learner's cognitive burden, achieving state-of-the-art performance on benchmarks and addressing the Task-Over-Fitting problem with a new metric.
Recently, meta-learning has been shown as a promising way to solve few-shot learning. In this paper, inspired by the human cognition process which utilizes both prior-knowledge and vision attention in learning new knowledge, we present a novel paradigm of meta-learning approach with three developments to introduce attention mechanism and prior-knowledge for meta-learning. In our approach, prior-knowledge is responsible for helping meta-learner expressing the input data into high-level representation space, and attention mechanism enables meta-learner focusing on key features of the data in the representation space. Compared with existing meta-learning approaches that pay little attention to prior-knowledge and vision attention, our approach alleviates the meta-learner's few-shot cognition burden. Furthermore, a Task-Over-Fitting (TOF) problem, which indicates that the meta-learner has poor generalization on different K-shot learning tasks, is discovered and we propose a Cross-Entropy across Tasks (CET) metric to model and solve the TOF problem. Extensive experiments demonstrate that we improve the meta-learner with state-of-the-art performance on several few-shot learning benchmarks, and at the same time the TOF problem can also be released greatly.