Learning Imbalanced Datasets with Label-Distribution …

← Back to document page

here assume the knowledge of the test label distribution, using which we design efficient methods that can scale easily to large-scale vision datasets with significant improvements. Meta-learning. Meta-learning is also used in improving the performance on imbalanced datasets or the few shot learning settings.

  Using, With, Design, Label, Distribution, Learning, Dataset, Imbalanced, Learning imbalanced datasets with label distribution