Return to Question

From what I can see most object detection NNs (Fast(er) R-CNN, YOLO etc) are trained on data including bounding boxes indicating where in the picture the objects are localised.

Are there algos that simply take the full picture + label annotations, and then on top of determining whether an object contain certain object(s) also indirectly

• learn to understand the appropriate bounding box(es) for objects?

From what I can see most object detection NNs (Fast(er) R-CNN, YOLO etc) are trained on data including bounding boxes indicating where in the picture the objects are localised.

Are there algos that simply take the full picture + label annotations, and then on top of determining whether an image contain certain object(s) also indirectly

• learn to understand the appropriate bounding box(es) for objects?

From what I can see most object detection NNs (Fast(er) R-CNN, YOLO etc) are trained on data including bounding boxes indicating where in the picture the objects are localised.

Are there algos that simply take the full picture + label annotations, and thereby do what standard induce that the picture contain certain object(s) and

• learn to understand the appropriate bounding box(es)?

From what I can see most object detection NNs (Fast(er) R-CNN, YOLO etc) are trained on data including bounding boxes indicating where in the picture the objects are localised.

Are there algos that simply take the full picture + label annotations, and then on top of determining whether an object contain certain object(s) also indirectly

• learn to understand the appropriate bounding box(es) for objects?