Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

YOLO: Real-Time Object Detection

pjreddie.com

Post reply on HN
Print view View original

1–10 of 63 posts

Re: YOLO: Real-Time Object Detection

#3

Post by deepsun »

It still seems to be using only the single frame, without past/present context. E.g. a dog sometimes is recognized as teddy bear for a split second.

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).

Re: YOLO: Real-Time Object Detection

#4

Post by JasonGenova25 »

deepsun wrote: post #3

It still seems to be using only the single frame, without past/present context. E.g. a dog sometimes is recognized as teddy bear for a split second. 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).

YOLO stands for "You Only Look Once" so I don't think this will ever become "continuous"

Re: YOLO: Real-Time Object Detection

#5

Post by razeonex »

deepsun wrote: post #3

It still seems to be using only the single frame, without past/present context. E.g. a dog sometimes is recognized as teddy bear for a split second. 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).

It maybe depends on the weights that you're loading with the model

Re: YOLO: Real-Time Object Detection

#6

Post by syntaxing »

Suprised to see this here since YOLO has been out for a while now. Shameless plug, I wrote an article on how to use use transfer learning on your custom dataset with the pretrained weights [1]. One of the downside of YOLO is that it uses his own deep learning library darknet. I find that the Tensorflow port dark flow easier to use but it haven't seen a v3 port yet.

[1] https://www.powu3.com/ml/yolo/

Re: YOLO: Real-Time Object Detection

#7

Post by saynay »

JasonGenova25 wrote: post #4
deepsun wrote: post #3

It still seems to be using only the single frame, without past/present context. E.g. a dog sometimes is recognized as teddy bear for a split second. 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).

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.

Post reply on HN