AI versus a giraffe with no spots
AI versus a giraffe with no spots
On July 31, 2023, a giraffe with no spots was born at Brights Zoo in Tennessee.
Image recognition algorithms are trained on a variety of images from around the internet, and/or on a few standard image datasets. But there likely haven’t been any spotless giraffes in their training data, since the last one to be born was probably in 1972 in Tokyo. How do they do when faced with photos of the spotless giraffe?
Here’s Multi-Modal In-Context Learning:
And InstructBLIP, which was more eloquent but also added lots of spurious detail.
More examples at AiWeirdness.com
Are these crummy image recognition models? Not unusually so. As far as I can tell with a brief poke around, MMICL and InstructBLIP are modern models (as of Aug 2023), fairly high up on the leaderboards of models answering questions about images. Their demonstration pages (and InstructBLIP’s paper) are full of examples of the models providing complete and sensible-looking answers about images.
Then why are they so bad at Giraffe With No Spots?
I can think of three main factors here:
- AI does best on images it’s seen before. We know AI is good at memorizing stuff; it might even be that some of the images in the examples and benchmarks are in the training datasets these algorithms used. Giraffe With No Spots may be especially difficult not only because the giraffe is unusual, but because it’s new to the internet.
- AI tends to sand away the unusual. It’s trained to answer with the most likely answer to your question, which is not necessarily the most correct answer.
- The papers and demonstration sites are showcasing their best work.Whereas I am zeroing in on their worst work, because it’s entertaining and because it’s a cautionary tale about putting too much faith in AI image recognition.