"Superresolution" AI is weird - it can't recover info that doesn't exist in the low-res input so it invents detail.
This is PULSE, whose task is to find a high-res image that matches the low-res input. It's better at finding some solutions than others.
https://aiweirdness.com/post/622002033086578688/depixellation-or-hallucination
This is PULSE, whose task is to find a high-res image that matches the low-res input. It's better at finding some solutions than others.
https://aiweirdness.com/post/622002033086578688/depixellation-or-hallucination
The AI tends to find matching faces in certain positions, so it can look weird if you give it something else.
I verified that yes, if you downscale the upscaled image on the right, you’ll get something that looks very much like the picture in the center. It's technically correct
I verified that yes, if you downscale the upscaled image on the right, you’ll get something that looks very much like the picture in the center. It's technically correct
The AI reconstructs what it’s been rewarded to see, and since it’s been trained to produce human faces, that’s what it will reconstruct. So if I were to feed it an image of a plush giraffe, for example
#PlushGiraffePerturbation
#PlushGiraffePerturbation
This AI can't ID a blurred face.
But a hypothetical AI that upscales low-res images to match faces in a police database would be both a horrifying misuse of this technology and not out of character with how law enforcement abuses facial recognition today https://www.washingtonpost.com/technology/2019/05/16/police-have-used-celebrity-lookalikes-distorted-images-boost-facial-recognition-results-research-finds/
But a hypothetical AI that upscales low-res images to match faces in a police database would be both a horrifying misuse of this technology and not out of character with how law enforcement abuses facial recognition today https://www.washingtonpost.com/technology/2019/05/16/police-have-used-celebrity-lookalikes-distorted-images-boost-facial-recognition-results-research-finds/
Speaking of what the AI has been rewarded to reconstruct - shortly after the authors released PULSE, people began to notice...THIS https://twitter.com/Chicken3gg/status/1274314622447820801
Several people, including the authors of the original paper on PULSE, found that the AI had a noticeable tendency to produce white faces, even if the input image hadn’t been of a white person. https://twitter.com/osazuwa/status/1274444300894572546?s=20
Biased AI is a well-documented phenomenon, but this particular image is striking because it's literally staring you in the face. https://www.theverge.com/21298762/face-depixelizer-ai-machine-learning-tool-pulse-stylegan-obama-bias
There could be many reasons that PULSE was biased.
Worth noting: The benchmark for upscaling faces is based on a dataset that is 90% white. An AI that's great at upscaling white faces but terrible otherwise could still qualify as state-of-the-art. This is definitely a problem.
Worth noting: The benchmark for upscaling faces is based on a dataset that is 90% white. An AI that's great at upscaling white faces but terrible otherwise could still qualify as state-of-the-art. This is definitely a problem.
A related problem: the huge lack of diversity in the field of artificial intelligence. Even an academic project with art as its main application matters & should not have gone all the way to publication before someone noticed that it was hugely biased. https://www.theguardian.com/technology/2019/apr/16/artificial-intelligence-lack-diversity-new-york-university-study
Several factors are contributing to the lack of diversity in AI, including anti-Black bias.
This report by @databoydg is essential reading. https://twitter.com/JanelleCShane/status/1275289565494775808?s=20
This report by @databoydg is essential reading. https://twitter.com/JanelleCShane/status/1275289565494775808?s=20
Ignorance is no excuse. AI's bias issues are catching up with it, and it's long past time.
These folks have studied AI bias for years. Follow them.
@timnitGebru @jovialjoy @ruha9 @rajiinio @safiyanoble
@Abebab @mer__edith @YESHICAN @mathbabedotorg
@MiaD @math_rachel @DataSciBae
These folks have studied AI bias for years. Follow them.
@timnitGebru @jovialjoy @ruha9 @rajiinio @safiyanoble
@Abebab @mer__edith @YESHICAN @mathbabedotorg
@MiaD @math_rachel @DataSciBae
Also follow @AnimaAnandkumar @minxdragon @databoydg @kdphd @katecrawford @geomblog @artsci00 @BlackAFinSTEM @black_in_ai @AJLUnited
Honestly, follow them ALL.
And if you have other follows to suggest, please let me know. I want to listen to more experts in this area.
Honestly, follow them ALL.
And if you have other follows to suggest, please let me know. I want to listen to more experts in this area.