5 datasets found

Tags: VQA

Filter Results

  • VQA-CPv2

    The VQA-CPv2 dataset is used to study the robustness of VQA methods against linguistic biases.

  • VQA-CP

    The VQA-CP dataset is a split of the VQA dataset, designed to test generalization skills across changes in the answer distribution between the training and the test sets.

  • VQA

    The VQA dataset is a large-scale visual question answering dataset that consists of pairs of images that require natural language answers.

  • VQA-Introspect and VQAv2

    The dataset used in the paper for Visual Question Answering (VQA) task, combining VQA-Introspect and VQAv2 datasets.

  • 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,...
You can also access this registry using the API (see API Docs).