Recognize Anything Dataset Card

Dataset details

Dataset type: These annotation files come from the Recognize Anything Model (RAM). RAM propose an automatic data engine to generate substantial image tags from image-text pairs.

Dataset date: Recognize Anything Dataset was collected in April 2023, by an automatic data engine proposed by RAM.

Paper or resources for more information: https://github.com/xinyu1205/recognize-anything

Where to send questions or comments about the model: https://github.com/xinyu1205/recognize-anything/issues

Intended use

Primary intended uses: The primary use of Recognize Anything is research on fundamental image recognition models.

Primary intended users: The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.