Multidimensional Belief Quantification for Label-Efficient Meta-Learning
This work addresses label efficiency in meta-learning for computer vision applications, offering incremental improvements in task selection and uncertainty quantification.
The paper tackles the problem of high labeling costs and computational overhead in meta-learning by proposing an uncertainty-aware task selection model that formulates a multidimensional belief measure to quantify and bound task uncertainty, enabling more efficient training. Experiments on real-world few-shot image classification tasks demonstrate its effectiveness.
Optimization-based meta-learning offers a promising direction for few-shot learning that is essential for many real-world computer vision applications. However, learning from few samples introduces uncertainty, and quantifying model confidence for few-shot predictions is essential for many critical domains. Furthermore, few-shot tasks used in meta training are usually sampled randomly from a task distribution for an iterative model update, leading to high labeling costs and computational overhead in meta-training. We propose a novel uncertainty-aware task selection model for label efficient meta-learning. The proposed model formulates a multidimensional belief measure, which can quantify the known uncertainty and lower bound the unknown uncertainty of any given task. Our theoretical result establishes an important relationship between the conflicting belief and the incorrect belief. The theoretical result allows us to estimate the total uncertainty of a task, which provides a principled criterion for task selection. A novel multi-query task formulation is further developed to improve both the computational and labeling efficiency of meta-learning. Experiments conducted over multiple real-world few-shot image classification tasks demonstrate the effectiveness of the proposed model.