> YOLOv3 is a good detector. It’s fast, it’s accurate. It’s
not as great on the COCO average AP between .5 and .95 IOU metric. But it’s very good on the old detection metric of .5 IOU. Why did we switch metrics anyway? The original
COCO paper just has this cryptic sentence: “A full discussion of evaluation metrics will be added once the evaluation server is complete”. Russakovsky et al report that that humans have a hard time distinguishing an IOU of .3 from .5! “Training humans to visually inspect a bounding box with IOU of 0.3 and distinguish it from one with IOU 0.5 is surprisingly difficult.”  If humans have a hard time telling the difference, how much does it matter?
> But maybe a better question is: “What are we going to
do with these detectors now that we have them?” A lot of the people doing this research are at Google and Facebook. I guess at least we know the technology is in good hands and definitely won’t be used to harvest your personal information and sell it to.... wait, you’re saying that’s exactly what it will be used for??
> Oh. Well the other people heavily funding vision research are
the military and they’ve never done anything horrible like killing lots of people with new technology oh wait.....
> I have a lot of hope that most of the people using computer vision are just doing happy, good stuff with it, like counting the number of zebras in a national park , or tracking their cat as it wanders around their house . But computer vision is already being put to questionable use and as researchers we have a responsibility to at least consider the harm our work might be doing and think ofways to mitigate it. We owe the world that much. In closing, do not @ me. (Because I finally quit Twitter).
> 1 The author is funded by the Office of Naval Research and Google.
> You can tell YOLOv3 is good because it’s very high and far to the left. Can you cite your own paper? Guess who’s going to try, this guy→
This guy cites.
At first I was a bit put down by the bloggish tone but it does not obfuscate nor impair communication of information, so yes, pretty good paper!
As an academic, I’ve now seen the light!
What genre of papers does this belong to? I want to read more.
Now coming to the question-
Is the input size and output size same that is why box top-left coordinated (bx, by) prediction corresponds to offset(cx) + prediction (sigma(tx)) and similar for y?
There's a ton of 'decade behind' stuff that runs in VMs on Win10 machines.
But, ”in turn, we receive support in taking our AI software to the next level of development”
I bet they are mainly looking for help. They are trying to figure out why their software is not capable to do what it is supposed to, and hoping someone can assist.
I’m ready to consult them on this if they are open to hear the bad news first...
The article could be clearer on this, but when it refers to "production", I think it means factories and logistics. (At least that's how I put together "production" in the headline with "implementing next-level production processes throughout its plants" from the first sentence.)
In other words, I think they use these algorithms in manufacturing systems, and they aren't putting this software into the cars' computers.