SerezD

/

mi_ml_gen

like 0

This PR significantly enhances the model card for the research artifact A Mutual Information Perspective on Multiple Latent Variable Generative Models for Positive View Generation.

Key improvements include:

• Adding license: mit and pipeline_tag: image-feature-extraction to the metadata for better discoverability at https://huggingface.co/models?pipeline_tag=image-feature-extraction.
• Including the full paper title, abstract, and links to the Hugging Face paper page and the official GitHub repository.
• Providing a detailed "Usage" section based on the GitHub README, which covers:
  • Installation steps.
  • Code snippets for generating multiple views, including visual examples.
  • Instructions and code snippets for training image feature encoders (SimSiam, Byol).
  • Instructions and code snippets for training and evaluating linear classifiers on extracted features.
• Adding the BibTeX citation for proper academic attribution.

These updates aim to make the model more accessible and easier to use for the community.