Meta-Learner with Linear Nulling
This work addresses the problem of few-shot learning for image classification, offering a novel method that is incremental in improving accuracy on standard benchmarks.
The paper tackles few-shot image classification by proposing a meta-learning algorithm that uses linear transformer null-space projection to quickly zero-force error signals, enabling reliable classification with limited data. It achieves state-of-the-art or near-best accuracies on Omniglot and miniImageNet datasets with a given model size.
We propose a meta-learning algorithm utilizing a linear transformer that carries out null-space projection of neural network outputs. The main idea is to construct an alternative classification space such that the error signals during few-shot learning are quickly zero-forced on that space so that reliable classification on low data is possible. The final decision on a query is obtained utilizing a null-space-projected distance measure between the network output and reference vectors, both of which have been trained in the initial learning phase. Among the known methods with a given model size, our meta-learner achieves the best or near-best image classification accuracies with Omniglot and miniImageNet datasets.