Prior-Knowledge and Attention-based Meta-Learning for Few-Shot Learning

Abstract

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.

arXiv comment15 pages

References in corpus (17)

• A Simple Framework for Contrastive Learning of Visual Representations
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Playing Atari with Deep Reinforcement Learning
• Recurrent Models of Visual Attention
• Matching Networks for One Shot Learning
• A Simple Neural Attentive Meta-Learner
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• RL${}^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
• Deep Clustering for Unsupervised Learning of Visual Features
• Few-Shot Learning with Graph Neural Networks
• Residual Attention Network for Image Classification
• Meta-Learning with Implicit Gradients
• TADAM: Task dependent adaptive metric for improved few-shot learning
• Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
• Is the deconvolution layer the same as a convolutional layer?
• Neural Machine Translation with Reconstruction

Cited by in corpus (1)

• K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations