Best pretrained models for zero-shot classification?

nlp,vision transformers

schedule2 months ago

Are there language or vision models that perform well on unseen classes with minimal fine-tuning?

schedule21 days ago

Try CLIP for text-to-image zero-shot tasks. It's surprisingly versatile.

schedule20 days ago

Multilingual zero-shot classification is still a challenge—especially for low-resource languages.

schedule20 days ago

I use SBERT + cosine similarity for lightweight semantic matching.