N-Shot Learning
- 1.
- 1.Instead of using class labels, we use some kind of vector representation for the classes, taken from a co-occurrence-after-svd or word2vec. - quite clever. This enables us to figure out if a new unseen class is near one of the known supervised classes. KNN can be used or some other distance-based classifier. Can we use word2vec for similarity measurements of new classes?Image by Dr. Timothy Hospedales, Yandexfor classification, we can use nearest neighbour or manifold-based labeling propagation.Image by Dr. Timothy Hospedales, Yandex Multiple category vectors? Multilabel zero-shot also in the video