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

YOLOv5: State-of-the-art object detection at 140 FPS

blog.roboflow.ai

Post reply on HN
Print view View original

51–60 of 136 posts

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#51

Post by homarp »

TehCorwiz wrote: post #29
jcims wrote: post #23

Earlier quoted context omitted.

>Facial recognition has very few applications outside of total surveillance. That's not really for you to decide, is it? You're absolutely free to have that opinion of course. >We should not respect those who lend it their time and effort. Also your choice of course. Facial recognition is essentially a light integration of powerful underlying technologies. Should 'we' ostracize those working on machine learning, comp…

You didn't really address the author's point which was that there don't appear to be compelling uses of facial technology beyond mass automated surveillance. I can't think of other uses and I'd be interested if you can come up with some.

Some compelling use:

1) assistance to recognizing people (because low vision, because memory fails, because you have a lot of photos...)

2) ensure candidate X is actually candidate X and not a paid person to take the exam in name of candidate X

3) door access control (to replace/in addition to access card)

4) having your own X-Ray (like in Amazon Prime): identify an actor/actress/model

5) having your personal robot addressing you by name

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#52

Post by monocasa »

anewdirection wrote: post #25
monocasa wrote: post #19

Earlier quoted context omitted.

I thought the real focus on the bad actors at this point was on gait detection. Works in civil unrest situations where everyone covers their face. Not the the difference matters that much.

Its not exclusive. Bad actors are working on whatever they are paid to build, by other bad actors with less technical acumen and more money. Edit: I should add, that most of the actual progress is being made by smart people who think its an interesting problem and are unaware or uncaring of the clear outcome of such tech.

In this case I meant bad actors as in who is funding the research with the idea of increasing surveillance for the purpose of squashing dissent.

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#53

Post by homarp »

homarp wrote: post #51
TehCorwiz wrote: post #29

Earlier quoted context omitted.

You didn't really address the author's point which was that there don't appear to be compelling uses of facial technology beyond mass automated surveillance. I can't think of other uses and I'd be interested if you can come up with some.

Some compelling use: 1) assistance to recognizing people (because low vision, because memory fails, because you have a lot of photos...) 2) ensure candidate X is actually candidate X and not a paid person to take the exam in name of candidate X 3) door access control (to replace/in addition to access card) 4) having your own X-Ray (like in Amazon Prime): identify an actor/actress/model 5) having your personal robot a…

also, having models that can run locally on "cheap enough" devices is also quite interesting that you more or less understand.

Compared to using API in the cloud or purchasing Hikvision cameras.

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#56

Post by sudosysgen »

eeZah7Ux wrote: post #49
rocauc wrote: post #2

EfficientDet was open sourced March 18 [1], YOLOv4 came out April 23 [2], and now YOLOv5 is out only 48 days later. In our initial look, YOLOv5 is 180% faster, 88% smaller, similarly accurate, and easier to use (native to PyTorch rather thank Darknet) than YOLOv4. [1] https://venturebeat.com/2020/03/18/google-ai-open-sources-ef... [2] https://arxiv.org/abs/2004.10934

> open sourced This is not a verb.

Arguably it became one.

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#57

Post by jcims »

descenter wrote: post #31
jcims wrote: post #23

Earlier quoted context omitted.

>Facial recognition has very few applications outside of total surveillance. That's not really for you to decide, is it? You're absolutely free to have that opinion of course. >We should not respect those who lend it their time and effort. Also your choice of course. Facial recognition is essentially a light integration of powerful underlying technologies. Should 'we' ostracize those working on machine learning, comp…

> Facial recognition is essentially a light integration of powerful underlying technologies. Should 'we' ostracize those working on machine learning, computer vision, network and distributed computing, etc? Couldn't you argue the same way against just about any kind of IED or booby trap? Yet people tend to ostracize those who make them more than they do people who make ball bearings and nails.

Who in Iraq was getting ostracized by their family and friends for making IEDs?

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#58

Post by nharada »

I welcome forward progress in the field, but something about this doesn't sit right with me. The authors have an unpublished/unreviewed set of results and they're already co-opting the YOLO name (without the original author) for it and all of this to promote a company? I guess this was inevitable when there's so much money in ML but it definitely feels against the spirit of the academic research community that they're building upon.

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#59

Post by heavyset_go »

homarp wrote: post #51
TehCorwiz wrote: post #29

Earlier quoted context omitted.

You didn't really address the author's point which was that there don't appear to be compelling uses of facial technology beyond mass automated surveillance. I can't think of other uses and I'd be interested if you can come up with some.

Some compelling use: 1) assistance to recognizing people (because low vision, because memory fails, because you have a lot of photos...) 2) ensure candidate X is actually candidate X and not a paid person to take the exam in name of candidate X 3) door access control (to replace/in addition to access card) 4) having your own X-Ray (like in Amazon Prime): identify an actor/actress/model 5) having your personal robot a…

> 2) ensure candidate X is actually candidate X and not a paid person to take the exam in name of candidate X

Can you imagine the bureaucratic nightmare that would be unleashed upon yourself if "the system" decides you aren't who you say you are because of the way you aged, an injury, surgery or a few new freckles?

This already happens sometimes with birth certificates and identity theft, and it's awful for those who have to experience it. I'd hate to have a black box AI inflicting that upon others for inexplicable reasons.

Re: YOLOv5: State-of-the-art object detection at 140 FPS

#60

Post by sillysaurusx »

foota wrote: post #45
sillysaurusx wrote: post #26

Earlier quoted context omitted.

Well, that didn't take long – our API endpoint keeled over. Luckily, you can fetch all the data directly from firebase: # fetch raw tag data $ curl -fsSL https://experiments-573d7.firebaseio.com/results/.json > tags.json $ du -hs tags.json 14M tags.json # fetch tag metadata (colors, remapping label names, possibly other stuff in the future) $ curl -fsSL https://experiments-573d7.firebaseio.com/user_meta/.json > tags_…

Can you set it up so that it's only available via cloud? I'm sure that would bother people, but is a better alternative to losing access or you going broke :)

We're motivated to keep this as open as possible. I really like the idea of an open dataset that continues to grow with time. If it keeps growing, then within a couple years it should have a vast quantity of tags on a variety of diverse datasets, which we hope might prove helpful.

If anyone wants to contribute, I started a patreon a few minutes ago: https://www.patreon.com/shawwn

Post reply on HN