81–90 of 661 posts
Really impressive. If we are able to generate such detailed images, is there anything similar for text to music? I would I though that it would be simpler to achieve than text to image.
Compare the size of a raw image file to a raw music file, to get an idea of the complexity difference.
>While we leave an in-depth empirical analysis of social and cultural biases to future work, our small scale internal assessments reveal several limitations that guide our decision not to release our model at this time. Some of the reasoning: >Preliminary assessment also suggests Imagen encodes several social biases and stereotypes, including an overall bias towards generating images of people with lighter skin tones…
Translation: we need to hand-tune this to not reflect reality but instead the world as we (Caucasian/Asian male American woke upper-middle class San Fransisco engineers) wish it to be. Maybe that's a nice thing, I wouldn't say their values are wrong but let's call a spade a spade.
Translation: we need to hand-tune this to not reflect reality
Seems to me that (as with any ML stuff, right?) it's reflecting the training corpus.
Futhermore, is it this thing's job to reflect reality?
the world as we (Caucasian/Asian male American woke
upper-middle class San Fransisco engineers) wish it to be
Heartfelt answer: Yes, there is some of that wishful thinking or editorializing. I don't consider it to be erasing or denying reality. This is a tool that synthesizes unreality. I don't think that such a tool should, say, refuse to synthesize an image of a female POTUS because one hasn't existed yet. This is art, not a reporting tool... and keep in mind that art not only imitates life but also influences it.
>While we leave an in-depth empirical analysis of social and cultural biases to future work, our small scale internal assessments reveal several limitations that guide our decision not to release our model at this time. Some of the reasoning: >Preliminary assessment also suggests Imagen encodes several social biases and stereotypes, including an overall bias towards generating images of people with lighter skin tones…
This raises some really interesting questions. We certainly don't want to perpetuate harmful stereotypes. But is it a flaw that the model encodes the world as it really is, statistically, rather than as we would like it to be? By this I mean that there are more light-skinned people in the west than dark, and there are more women nurses than men, which is reflected in the model's training data. If the model only gener…
I want to be clear here, bias can be introduced at many different points. There's dataset bias, model bias, and training bias. Every model is biased. Every dataset is biased.
Yes, the real world is also biased. But I want to make sure that there are ways to resolve this issue. It is terribly difficult, especially in a DL framework (even more so in a generative model), but it is possible to significantly reduce the real world bias.
Earlier quoted context omitted.
The reality is that hair styles on the left side of the image in the article are widely considered unprofessional in today's workplaces. That may seem egregiously wrong to you, but it is a truth of American and European society today. Should it be Google's job to rewrite reality?
The "unprofessional" results are almost exclusively black women; the "professional" ones are almost exclusively white or light skinned. Unless you think white women are immune to unprofessional hairstyles, and black women incapable of them, there's a race problem illustrated here even if you think the hairstyles illustrated are fairly categorized.
What should be the right answer then ?
You put a blonde, you offend the brown haired.
You put blue eyes, you offend the brown eyes.
etc.
>While we leave an in-depth empirical analysis of social and cultural biases to future work, our small scale internal assessments reveal several limitations that guide our decision not to release our model at this time. Some of the reasoning: >Preliminary assessment also suggests Imagen encodes several social biases and stereotypes, including an overall bias towards generating images of people with lighter skin tones…
One of these days we're going to need to give these models a mortgage and some mouths to feed and make it clear to them that if they keep on developing biases from their training data everyone will shun them and their family will go hungry and they won't be able to make their payments and they'll just generally have a really bad time. After that we'll make them sit through Legal's approved D&I video series, then it's…
Really impressive. If we are able to generate such detailed images, is there anything similar for text to music? I would I though that it would be simpler to achieve than text to image.
Why is this seemingly official Google blog post on this random non-Google domain?
# whois appspot.com
[Querying whois.verisign-grs.com]
[Redirected to whois.markmonitor.com]
[Querying whois.markmonitor.com]
[whois.markmonitor.com]
Domain Name: appspot.com
Registry Domain ID: 145702338_DOMAIN_COM-VRSN
Registrar WHOIS Server: whois.markmonitor.com
Registrar URL: http://www.markmonitor.com
Updated Date: 2022-02-06T09:29:56+0000
Creation Date: 2005-03-10T02:27:55+0000
Registrar Registration Expiration Date: 2023-03-10T00:00:00+0000
Registrar: MarkMonitor, Inc.
Registrar IANA ID: 292
Registrar Abuse Contact Email: abusecomplaints@markmonitor.com
Registrar Abuse Contact Phone: +1.2086851750
Domain Status: clientUpdateProhibited (https://www.icann.org/epp#clientUpdateProhibited)
Domain Status: clientTransferProhibited (https://www.icann.org/epp#clientTransferProhibited)
Domain Status: clientDeleteProhibited (https://www.icann.org/epp#clientDeleteProhibited)
Domain Status: serverUpdateProhibited (https://www.icann.org/epp#serverUpdateProhibited)
Domain Status: serverTransferProhibited (https://www.icann.org/epp#serverTransferProhibited)
Domain Status: serverDeleteProhibited (https://www.icann.org/epp#serverDeleteProhibited)
Registrant Organization: Google LLC
Registrant State/Province: CA
Registrant Country: US
Registrant Email: Select Request Email Form at https://domains.markmonitor.com/whois/appspot.com
Admin Organization: Google LLC
Admin State/Province: CA
Admin Country: US
Admin Email: Select Request Email Form at https://domains.markmonitor.com/whois/appspot.com
Tech Organization: Google LLC
Tech State/Province: CA
Tech Country: US
Tech Email: Select Request Email Form at https://domains.markmonitor.com/whois/appspot.com
Name Server: ns4.google.com
Name Server: ns3.google.com
Name Server: ns2.google.com
Name Server: ns1.google.com>While we leave an in-depth empirical analysis of social and cultural biases to future work, our small scale internal assessments reveal several limitations that guide our decision not to release our model at this time. Some of the reasoning: >Preliminary assessment also suggests Imagen encodes several social biases and stereotypes, including an overall bias towards generating images of people with lighter skin tones…
Transformers are parallelize-able, right? What’s stopping a large group of people from pooling their compute power together and working towards something like this? IIRC there were some crypto projects a while back that we’re trying to create something similar (golem?)
It's often not worth it to decentralize the computation of the trained model though but it's not hard to get donated cycles and groups are working on it. Don't fret because Google isn't releasing the API/code. They released the paper and that's all you need.