Technical GlossaryComputer Vision
Anchor Boxes
TR: Anchor Box
In One Line
A design approach that facilitates object detection by using predefined candidate boxes of different scales and aspect ratios.
The anchor box approach makes object detection more structured than directly predicting free-form coordinates. The model classifies and refines predefined box templates. This can be especially useful in scenes containing objects at multiple scales and aspect ratios. However, anchor design and count directly affect both accuracy and computational cost.
You Might Also Like
Explore these concepts to continue your artificial intelligence journey.
