4 datasets found

Groups: Compositional Zero-Shot Learning

Filter Results

  • UT-Zappos50K

    The UT-Zappos50K dataset is a fine-grained shoe catalog, characterized by its smaller scale and relatively stable and simple content.

  • C-GQA

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

  • MIT-States

    The dataset used in the paper is not explicitly described, but it is mentioned that the authors used MIT-States, Fashion200k, and COCO 2017 Panoptic Segmentation datasets for...

  • Graph-Injected Soft Prompting for Compositional Zero-Shot Learning

    The proposed GIPCOL framework for compositional zero-shot learning (CZSL) using CLIP-based prompting.