Building on this method, we perform an extensive analysis and find that sampling uniformly over episode difficulty outperforms other sampling schemes, including curriculum and easy-/hard-mining. As the proposed sampling method is algorithm agnostic, we can leverage these insights to improve few-shot learning accuracies across many episodic training algorithms.

Neural Information Processing Systems http://nips.cc/

In particular, we conjecture and empirically illustrate that, the celebrated batch normalization (BN) technique actually adapts the "normalized" bias such that it approximates

We present a new approach to learn compressible representations in deep architectures with an end-to-end training strategy.

Existing machine learning algorithms including deep neural networks achieve good performance in cases where the training and the test data are sampled from the same distribution. While this is a reasonable assumption to make, it might not hold true in practice.

We argue that this GAN-based approach can help few-shot classifiers to learn sharper decision boundary, which could generalize better.

FP method and the minorization-maximization theory to verify the convergence.

Existing machine learning algorithms including deep neural networks achieve good performance in cases where the training and the test data are sampled from the same distribution. While this is a reasonable assumption to make, it might not hold true in practice.

We argue that this GAN-based approach can help few-shot classifiers to learn sharper decision boundary, which could generalize better.

NAS collect a large number of samples (e.g., accuracy and latency) from a target