Meta-Learning with Individualized Feature Space for Few-Shot Classification
Meta-learning provides a promising learning framework to address few-shot classification tasks. In existing meta-learning methods, the meta-learner is designed to learn about model optimization, parameter initialization, or similarity metric. Differently, in this paper, we propose to learn how to create an individualized feature embedding specific to a given query image for better classifying, i.e., given a query image, a specific feature embedding tailored for its characteristics is created accordingly, leading to an individualized feature space in which the query image can be more accurately classified. Specifically, we introduce a kernel generator as meta-learner to learn to construct feature embedding for query images. The kernel generator acquires meta-knowledge of generating adequate convolutional kernels for different query images during training, which can generalize to unseen categories without fine-tuning. In two standard few-shot classification data sets, i.e. Omniglot, and \emph{mini}ImageNet, our method shows highly competitive performance.
PDF Abstract
