Update pipeline tag to zero-shot-image-classification
#2
by
nielsr
HF Staff
- opened
This PR updates the pipeline_tag in the model card from image-text-to-text to zero-shot-image-classification.
The paper abstract states that UniME learns "discriminative representations for diverse downstream tasks," particularly for "image-text retrieval and clustering." The quick start guide also demonstrates computing a similarity score between image and text embeddings. This functionality is more aligned with discriminative tasks like zero-shot classification and retrieval rather than text generation or translation.
Changing the pipeline_tag will improve the model's discoverability on the Hugging Face Hub, allowing users to find it under the most relevant category for its primary use case.