Computer vision and multimodal learning · MLD-0882
Patch embedding
A vector representation of a local image patch used as an input token.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Turn an image into a transformer token sequence.
Original caveat
Patch size controls the tradeoff between detail and sequence length.
Context and aliases
Level: Intermediate. Stages: Architecture · Training · Inference.
Tags: DL · Vision · Multimodal.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Learning Transferable Visual Models From Natural Language Supervision ↗ · Consulted
- Deep Learning: online textbook ↗ · Consulted
- PyTorch neural-network layers ↗ · Reference link
- Original reference URL ↗