Directly Optimizing IoU for Bounding Box Localization. (arXiv:2304.07256v1 [cs.CV])

Object detection has seen remarkable progress in recent years with the
introduction of Convolutional Neural Networks (CNN). Object detection is a
multi-task learning problem where both the position of the objects in the
images as well as their classes needs to be correctly identified. The idea here
is to maximize the overlap between the ground-truth bounding boxes and the
predictions i.e. the Intersection over Union (IoU). In the scope of work seen
currently in this domain, IoU is approximated by …

arxiv box cnn convolutional neural networks detection images introduction localization loss multi-task learning networks neural networks objects predictions progress work