I'm confused by the fact that YOLO** can have multiple bounding boxes per cell, but there is only one class vector. Does YOLO allow the truth/training to have more than one object in a cell, each with a different class? If so, how are the classes of each box encoded into the output and how does the loss function manage it?

** "You Only Look Once": https://arxiv.org/pdf/1506.02640.pdf



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.