Vision Encoder

Definitions

1. A model component that converts image or visual input into encoded representations usable by downstream systems. Vision encoders are key building blocks in image classification, retrieval, captioning, and multimodal models.

   In plain English: A component that turns images into encoded representations for AI use.

   Example: "They reused the vision encoder for both screenshot retrieval and downstream chart-description generation."

Related Terms

• Image Encoder
• Image Tokenizer
• Vision Feature
• Vision Model
• Vision Task
• Visual Grounding
• Visual Instruction
• Visual Understanding