2 datasets found

Tags: compositional zero-shot learning

Filter Results
  • C-GQA

    The C-GQA dataset is a large-scale dataset for compositional zero-shot learning, containing 413 attributes and 674 objects.
  • CLEVR

    CLEVR images contain objects characterized by a set of attributes (shape, color, size and material). The questions are grouped into 5 categories: Exist, Count, CompareInteger,...