@article{antoniou_assume_2019, title = {Assume, {Augment} and {Learn}: {Unsupervised} {Few}-{Shot} {Meta}-{Learning} via {Random} {Labels} and {Data} {Augmentation}}, shorttitle = {Assume, {Augment} and {Learn}}, url = {http://arxiv.org/abs/1902.09884}, abstract = {The field of few-shot learning has been laboriously explored in the supervised setting, where per-class labels are available. On the other hand, the unsupervised few-shot learning setting, where no labels of any kind are required, has seen little investigation. We propose a method, named Assume, Augment and Learn or AAL, for generating few-shot tasks using unlabeled data. We randomly label a random subset of images from an unlabeled dataset to generate a support set. Then by applying data augmentation on the support set's images, and reusing the support set's labels, we obtain a target set. The resulting few-shot tasks can be used to train any standard meta-learning framework. Once trained, such a model, can be directly applied on small real-labeled datasets without any changes or fine-tuning required. In our experiments, the learned models achieve good generalization performance in a variety of established few-shot learning tasks on Omniglot and Mini-Imagenet.}, urldate = {2020-03-19}, journal = {arXiv:1902.09884 [cs, stat]}, author = {Antoniou, Antreas and Storkey, Amos}, month = mar, year = {2019}, note = {arXiv: 1902.09884}, keywords = {Computer Science - Machine Learning, Statistics - Machine Learning}, }