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

Facebook open-sources Detectron

research.fb.com

Post reply on HN
Print view View original

131–140 of 188 posts

Re: Facebook open-sources Detectron

#131

Post by csallen »

0xTJ wrote: post #118
kurtisc wrote: post #81

Earlier quoted context omitted.

For the car captchas, I've found actually clicking all the boxes with part of a car will always be a wrong answer (distinct from when it just makes you answer twice). Instead, you have to click on the squares that you know it thinks are cars. This creates a twisted Turing test situation where, to prove you are a human, you have to pretend to be a machine's idea of what a human is.

Does it tell you that you're wrong, or simply give you another set. If it is just giving you another set, it may be that it thinks that you can provide more useful data.

It just gives you another set, but it's so frustrating and annoying as a user that I can't believe they're doing this on purpose.

Re: Facebook open-sources Detectron

#132

Post by thom »

kurtisc wrote: post #81
megous wrote: post #7

So is this the end of Google captchas asking for where the car/sign/whatever is? Will there be a final battle of AIs, where they will kill each other, and the unfettered access to websites over VPN/tor wins and laughs the last laugh?

For the car captchas, I've found actually clicking all the boxes with part of a car will always be a wrong answer (distinct from when it just makes you answer twice). Instead, you have to click on the squares that you know it thinks are cars. This creates a twisted Turing test situation where, to prove you are a human, you have to pretend to be a machine's idea of what a human is.

I went through exactly this today. Wasn't sure if it was the computer being dumb, or other people missing corners of signs or bridges etc. Still, takes me 5 goes every time.

Re: Facebook open-sources Detectron

#133

Post by megous »

culerawo wrote: post #77
lotsofcows wrote: post #72

Earlier quoted context omitted.

Neither. When Google finds someone willing to train its AI for free, it likes to take advantage.

You are a bit sarcastic. What can a user do? Either he continues solving "train their AI for free" until the let you move on or you leave the site?

You can complain to the site operator. Google is not forcing their captcha on websites. If enough people do that, perhaps site operator(s) will take notice. Tell them exactly what you don't like so they don't eventually change to different vendor, but same annoying captcha tech.

Re: Facebook open-sources Detectron

#134

Post by spyder »

mcintyre1994 wrote: post #93
schrep wrote: post #26

Earlier quoted context omitted.

Doesn’t mean I’m right :) - see above as he had a point.

Assuming from context you're CTO of Facebook, the facebook.com/schrep link in your profile isn't working: This page isn't available. The link you followed may be broken, or the page may have been removed.

The link only works if you are logged in, otherwise it says the page not found, which is wrong message because it makes you think it doesn't exists even if you login.

Re: Facebook open-sources Detectron

#135

Post by yohann305 »

my overall feeling as someone that wants to start getting into visual recognition is that there are a bunch of great libraries/ecosystems to choose from and all of them have pros and cons, but i honestly don't want to make the wrong decision and end up being stuck later on. Anyone here has any advise on what i should use to have a camera(rpi) recognize most common objects and then add a layer where we can teach specific objects, ie (putting a name on a person or a pet), thank you!

Re: Facebook open-sources Detectron

#136

Post by neogodless »

Jaruzel wrote: post #79
jraph wrote: post #55

Earlier quoted context omitted.

Has someone ever tried to submit images from Google captchas to Google Images? An answer like "This is definitely a sign" from Google Images would be funny.

I just tried it: http://www.jaruzel.com/files/streetsign.jpg :)

Now try it with the Speed Limit sign. Does that count as a "street sign" or only ones with street names?!

Re: Facebook open-sources Detectron

#137

Post by nerdponx »

kurtisc wrote: post #81
megous wrote: post #7

So is this the end of Google captchas asking for where the car/sign/whatever is? Will there be a final battle of AIs, where they will kill each other, and the unfettered access to websites over VPN/tor wins and laughs the last laugh?

For the car captchas, I've found actually clicking all the boxes with part of a car will always be a wrong answer (distinct from when it just makes you answer twice). Instead, you have to click on the squares that you know it thinks are cars. This creates a twisted Turing test situation where, to prove you are a human, you have to pretend to be a machine's idea of what a human is.

Street signs are a problem as well. Is the post part of the sign or not?

Re: Facebook open-sources Detectron

#138

Post by notyourwork »

newscracker wrote: post #2

This looks amazing from the computing point of view (and is an achievement of sorts), yet the confidence percentages are lower than what an average human might be able to solve for (like in the case of CAPTCHA tests). Meanwhile, I wonder about the human costs if systems like these are adopted for purposes where they may be ill suited for, especially cases where their confidence scores are ignored (or mistakenly assum…

Care to give any examples of scenarios you are concerned about?

Re: Facebook open-sources Detectron

#139

Post by dboreham »

kurtisc wrote: post #81
megous wrote: post #7

So is this the end of Google captchas asking for where the car/sign/whatever is? Will there be a final battle of AIs, where they will kill each other, and the unfettered access to websites over VPN/tor wins and laughs the last laugh?

For the car captchas, I've found actually clicking all the boxes with part of a car will always be a wrong answer (distinct from when it just makes you answer twice). Instead, you have to click on the squares that you know it thinks are cars. This creates a twisted Turing test situation where, to prove you are a human, you have to pretend to be a machine's idea of what a human is.

I find the same thing with the road signs : other people are giving (imho) the wrong answer by not including squares that cover a small, but non-zero part of the sign.

Re: Facebook open-sources Detectron

#140

Post by Jaruzel »

Spare_account wrote: post #88
Jaruzel wrote: post #85

Earlier quoted context omitted.

Your https-everywhere is doing it wrong. I don't have an SSL on my personal site (no requirement to). I do have SSL on other domains that share that IP however.

I'm not expert on this but what I'm seeing is that port 443 is serving up a response when jaruzel.com is requested on that port. While you may not be actively advertising that domain with https URLs, it is valid for clients to request one speculatively. There isn't a valid cert for that domain and for some reason for server is offering a different one. Presumably you need to unbind 443 from that host header name (thi…

So...

I have an IP... that IP points to a router, that router port-forwards ports 80 and 443 blindly to a web server, on that web server is a bunch of websites. IIS knows which ones to serve to clients based on a) the host-header, and b) the port.

jaruzel.com:443 is not valid, but because I run an older version of IIS[1], that does not support SNI, the cert is bound to the port, not the host-header. As such any domain name that points to the IP will dump you at that cert if you try to connect on port 443.

Hope this clears up any confusion. :)

---

[1] for um... reasons.

Post reply on HN