Reviews: Learning to Model the Tail

Summary ------- The paper proposes an approach for transfer learning for multi-class classification problems that aids the learning of categories with few training examples (the categories in the tail of the distribution of numbers of examples per category). It is based on ideas of meta-learning: it builds a (meta-)model of the dynamics that accompany the change in model parameters as more training data is made available to a classifier. Specifically, the proposed approach takes inspiration from existing work on meta-learning [20] but extends it by applying it to CNNs, utilizing deep residual networks as the meta-model, and applying the framework to a general'long-tail problem' setting in which the number of training examples available is different and not fixed between categories. Experiments are conducted on curated versions of existing datasets (curated such that they exhibit strong long-tail distributions): SUN-397 [13], Places [7], and ImageNet [5]. The performance of the proposed method is demonstrated to be considerably higher than several more adhoc baselines from the literature.