This is the supplementary material of paper "Towards Enabling Meta-Learning from Target Models". We give implementation details, more discussions, and more experiment results in this material.

Meta-learning approaches enable machine learning systems to adapt to new tasks given few examples by leveraging knowledge from related tasks. However, a large number of meta-training tasks are still required for generalization to unseen tasks during meta-testing, which introduces a critical bottleneck for real-world problems that come with only few tasks, due to various reasons including the difficulty and cost of constructing tasks. Recently, several task augmentation methods have been proposed to tackle this issue using domain-specific knowledge to design augmentation techniques to densify the meta-training task distribution.

A.1 Datasets We use two standardized few-shot image classification datasets. Mini-ImageNet: This dataset [58] is a subset of ImageNet [10] and consists of 64 classes for training, 16 for validation, and 20 for testing. There are 600 images per class, with images of size 84 84. Multiple versions of this dataset exist in the literature; we use the version by Ravi and Larochelle [43]. Tiered-ImageNet: A larger subset of ImageNet, Tiered-ImageNet [45] consists of 608 classes split into 351, 97, and 160 for training, validation, and testing, respectively.

We conduct a systematic comparison of methods in a variety of domains, varying thenumber oflabeled instances available inthetargetdomain (k), as well as the number of target-domain classes.

In this experiment, we modify ProtoNet slightly to fit regression problem. In detail, we try to meta-learn an embedding functionφ: R R100, with assistance of which the similarity-based regressionmodelg(;{φ(xi)|(xi,yi) S})workswellacrossalltasks.