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

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

facebook.com

Post reply on HN
Print view View original

11–20 of 46 posts

Re: DeepFace: Closing the Gap to Human-Level Performance in Face Verification

#11

Post by timdumol »

fchollet wrote: post #9

Important to note: - they still need 1000 labeled samples per identity - their network can only handle 4000 distinct identities (at 97.25% accuracy) at a time It's still a very worrying development for online and offline privacy.

Actually, based on my reading of the paper, it seems that they learn a representation using one data set (the one with 1000 labeled samples per identity), then use that representation to classify on other training sets (like the Labeled Faces in the Wild, which has 13,323 photos of 5,749 celebrities). In fact, from what I can tell from section 5.1, they seemed to use face pairs (and so trained on 1 sample per person, and then tested on the other sample).

tl;dr: They don't need 1,000 labeled samples per identity (once done with the representation phase), and they achieved 97.25% accuracy on ~6,000 distinct identities, with only one training photo per identity.

Re: DeepFace: Closing the Gap to Human-Level Performance in Face Verification

#13

Post by ta_fbp »

bayesianhorse wrote: post #10
fchollet wrote: post #9

Important to note: - they still need 1000 labeled samples per identity - their network can only handle 4000 distinct identities (at 97.25% accuracy) at a time It's still a very worrying development for online and offline privacy.

Actually no. For one thing, this isn't exactly a stealthy or cheap thing to do. It involves datacenters full of computing resources even for 4000 identies. I also don't believe it's so much a privacy issue. If I upload pictures to facebook I actually want them to be seen by human beings. The face-recognition only helps with that. If facebook recognizes me on a picture someplace else, I actually rather want to know ab…

Privacy issue is not about what you want, it's about what can be done (and often is without you knowing).

Automated facial recognition is a serious privacy concern, it's not just about the slimy despicable thing facebook is. For example, in the uk where there are more cctv video feed than people to watch them, an automated facial recognition can track you around constantly. Their current automatic number plate recognition is already a serious privacy concern.

Remember 7th cube's voyeur's dream[1] released in 2005? the same but with more camera now being able to identify you based on your facial features. [1]: http://www.pouet.net/prod.php?which=16410

Re: DeepFace: Closing the Gap to Human-Level Performance in Face Verification

#14

Post by bovermyer »

phpnode wrote: post #2

wow, does anyone apart from facebook and the government actually want facebook to do this? it's pretty terrifying

I do. Assuming that Facebook uses it in what appears to be the logical choice (auto-tagging photos), this would be a fantastic way to find photos of me that I don't already know about.

Re: DeepFace: Closing the Gap to Human-Level Performance in Face Verification

#15

Post by beagle3 »

fchollet wrote: post #8
visarga wrote: post #5

Earlier quoted context omitted.

deepfacebook Btw, does this software match faces to people or just draws a rectangle around faces?

It matches your face to your name with 97.25% accuracy, assuming that they have at least 1000 labeled photos of you to start with.

1 or 2 photos are enough for that accuracy. The 1000 photos were only needed in finding the right face representation.

Re: DeepFace: Closing the Gap to Human-Level Performance in Face Verification

#16

Post by reader5000 »

scotth wrote: post #12

It's surprising to me that there isn't a single positive comment in this thread considering how amazing this is. Sure, it has other implications, but were we really hoping to prevent computers from recognizing faces permanently?

"Luddite news"

Re: DeepFace: Closing the Gap to Human-Level Performance in Face Verification

#17

Post by cs702 »

The key innovation is an accurate, reliable method for rotating faces so they're 'looking straight at the camera' before feeding them to a deep neural network. They call this 3D photo rotation process "frontalization." Figure 1 on page 2 of the paper shows at a very high level how this is being done. Very nice!

Re: DeepFace: Closing the Gap to Human-Level Performance in Face Verification

#18

Post by adyus »

ta_fbp wrote: post #13
bayesianhorse wrote: post #10

Earlier quoted context omitted.

Actually no. For one thing, this isn't exactly a stealthy or cheap thing to do. It involves datacenters full of computing resources even for 4000 identies. I also don't believe it's so much a privacy issue. If I upload pictures to facebook I actually want them to be seen by human beings. The face-recognition only helps with that. If facebook recognizes me on a picture someplace else, I actually rather want to know ab…

Privacy issue is not about what you want, it's about what can be done (and often is without you knowing). Automated facial recognition is a serious privacy concern, it's not just about the slimy despicable thing facebook is. For example, in the uk where there are more cctv video feed than people to watch them, an automated facial recognition can track you around constantly. Their current automatic number plate recogn…

This can already be done by someone who truly wants to keep an eye on you, only it takes more manpower (well, detective power).

This is simply the same trend as ATMs replacing (some) bank tellers many years ago.

Will it be easier to perform and abuse mass surveillance? Sure. Will people with something important to hide still wear disguises? I'd bet yes.

My stance is that we can't fight progress, but we can start fighting the people bent on abusing the powers that progress bring. Identifying them is another issue (perhaps some form of facial recognition? :)

Re: DeepFace: Closing the Gap to Human-Level Performance in Face Verification

#19

Post by weezer »

cs702 wrote: post #17

The key innovation is an accurate, reliable method for rotating faces so they're 'looking straight at the camera' before feeding them to a deep neural network. They call this 3D photo rotation process "frontalization." Figure 1 on page 2 of the paper shows at a very high level how this is being done. Very nice!

Just a little background the paper itself doesn't provide:

The 3-d modeling and rotation is building on the work Yaniv did as part of Face.com (face recognition startup), which was acquired by Facebook.com. Studied here: http://vis-www.cs.umass.edu/lfw/results.html

Also Marc'Aurelio was just hired away from Google and is a deep learning expert.

Re: DeepFace: Closing the Gap to Human-Level Performance in Face Verification

#20

Post by normloman »

scotth wrote: post #12

It's surprising to me that there isn't a single positive comment in this thread considering how amazing this is. Sure, it has other implications, but were we really hoping to prevent computers from recognizing faces permanently?

No, we were just hoping to prevent creeps like facebook from using it to tailor advertising.
Post reply on HN