This Model Completely Crashed Computer Vision.

Author(s): Julia Originally published on Towards AI. Why is everyone obsessed with YOLO? And no I don’t talk about the 2012 mantra “You Only Live Once”. For years, computers struggled to “see” the world. Object detection, the task of finding and identifying objects in images, was slow and complex. Traditional models used a multi-step process. They scanned an image, proposed regions, and then classified those regions. This was accurate but painfully slow. Yolo traffic predictions, image souurce: