no code implementations • 22 Aug 2023 • Thomas P. O'Connell, Tyler Bonnen, Yoni Friedman, Ayush Tewari, Josh B. Tenenbaum, Vincent Sitzmann, Nancy Kanwisher
Finally, we find that while the models trained with multi-view learning objectives are able to partially generalize to new object categories, they fall short of human alignment.
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.