# zero-shot

> Browse 2 items tagged with zero-shot.

## Items

- [Zero-Shot Classification with Embeddings](https://vectordb.ever.works/items/zero-shot-classification-with-embeddings) — Using vector embeddings to classify items into categories without training data for those specific categories. Leverages semantic similarity between text and category descriptions for instant classification.
- [ImageBind](https://vectordb.ever.works/items/imagebind) — Meta's groundbreaking multimodal embedding model that learns a joint embedding space across six modalities (images, text, audio, depth, thermal, IMU) using only image-paired data, enabling cross-modal retrieval and zero-shot capabilities.

---

_Canonical page: https://vectordb.ever.works/tags/zero-shot_