DeepGlint-AI

/

mlcd-vit-large-patch14-336

like 10

Follow

DeepGlint 26

This PR significantly updates the model card for the rice-vit-large-patch14-560 model to accurately reflect its association with the paper "Region-based Cluster Discrimination for Visual Representation Learning" (RICE).

Key changes include:

• Updating the primary paper link to the correct RICE paper (https://huggingface.co/papers/2507.20025).
• Adding library_name: transformers to enable the "How to use" widget, as the model is compatible with the Transformers library.
• Refining the pipeline_tag from feature-extraction to image-feature-extraction for better discoverability.
• Incorporating comprehensive sections from the official GitHub repository's RICE section, including "Highlights", "Experiments" (with the relevant image, replacing outdated MLCD tables), "How to use" (sample code), "Visualize Semantic Features", "ModelZoo", and "Citation".
• Adding the paper abstract for a detailed overview.

This ensures the model card provides precise and up-to-date information for users.