You Only Look Once (YOLO) is an object detection system. It applies a single neural network to the full image. This network divides the image into regions and predicts bounding boxes and probabilities for each region. These bounding boxes are weighted by the predicted probabilities. YOLO makes predictions with a single network evaluation, which makes it extremely fast.
There are three versions of YOLO available as of May 2018.
- [YOLOv3]: Joseph Redmon, Ali Farhadi, "YOLOv3: An Incremental Improvement", arXiv 2018.
- [YOLOv2]: Joseph Redmon and Ali Farhadi, "YOLO9000: Better, Faster, Stronger", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017, pp. 6517-6525.
- [YOLOv1]: Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi, "You Only Look Once: Unified, Real-Time Object Detection", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 2016, pp. 779-788.