Questions
- How does the region proposal technique generate proposals?
 - How is IoU calculated if there are multiple objects in an image?
 - Why is Fast R-CNN faster than R-CNN?
 - How does RoI pooling work?
 - What is the impact of not having multiple layers after obtaining a feature map when predicting bounding-box corrections?
 - Why do we have to assign a higher weight to regression loss when calculating overall loss?
 - How does non-max suppression work?
 
Learn more on Discord
Join our community’s Discord space for discussions with the authors and other readers:
