AI engineering glossary · Computer vision
What is Fast R-CNN?
Fast R-CNN: An improved R-CNN that runs the CNN once on the whole image and then pools features for each proposed region using RoI pooling. Sharing the computation made training and inference much faster.
Fast R-CNN: an example
One backbone pass over a photo yields a feature map from which 2,000 proposals are read out.
Related terms
More Computer vision terms
- Faster R-CNN
- Feature descriptor
- Feature detection
- Feature map
- Feature matching
- Feature pyramid network
- Fine-tuning
- Fully convolutional network
Where you learn it
Fast R-CNN is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.