yeah it’s easy to fix those with a filter on the predictions. could use bayesian approach or just smooth using a majority vote over rolling window of say 3 frames...
Re:YOLO: Real-Time Object Detection
by JasonGenova25 on Tuesday April 02, 2019 @03:03PM
(#19557501)
YOLO stands for "You Only Look Once" so I don't think this will ever become "continuous"
AFAIK, the 'Look Once' part refers to other systems that re-ran a section of the frame at a time through an object detector, resulting in a lot of reprocessing.
You could still look only once, but have that look include multiple sequential frames. Or do something like an LSTM of frames.
Re:YOLO: Real-Time Object Detection
by JasonGenova25 on Tuesday April 02, 2019 @04:07PM
(#19558056)
Good point. I hadn't considered this.
For each frame, it returns a list of candidate detections with confidence values if I remember correctly. Should be pretty straightforward to make it smooth using that.
Is there any "continuous" models for that? Sounds like a simple bayesian post-processing would do a great deal (e.g. recording the probability of dogs mutating to teddy bears as very low).