|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Few-shot classification aims to recognize novel categories with only few labeled images in each class.
Extensive experiments on the proposed benchmark are performed to evaluate state-of-art meta-learning approaches, transfer learning approaches, and newer methods for cross-domain few-shot learning.
In our final results, we combine the novel method with the baseline method in a simple ensemble, and achieve an average accuracy of 73. 78% on the benchmark.