Variadic Learning by Bayesian Nonparametric Deep Embedding

no code implementations • 27 Sep 2018 • Kelsey R Allen, Hanul Shin, Evan Shelhamer, Josh B. Tenenbaum

On the standard few-shot learning benchmarks of Omniglot and mini-ImageNet, BANDE equals or improves on the state-of-the-art for semi-supervised classification.

Clustering Few-Shot Learning +1