YOLO (detector)

📖 Full definition

YOLO (You Only Look Once) is a family of object detection models known for speed. In face recognition, a lightweight version of YOLO is typically used to detect faces in an image before passing them to an embedding model. Without this step, the AI would not know where to look.

💡 Concrete example

When you upload a photo to Look Like Me, a lightweight YOLO-family detector first locates the face, then the embedding model computes the geometric signature on that area. If no face is detected, the analysis returns a clear error so you can retry with another photo.

🔄 Synonyms

You Only Look Once

🔗 See also

• ArcFace →
• Deep learning →