@alexjc's Threads
Impressive! There has been significant progress in GANs over the past few years, but that's not really what we're seeing here... [1/8]
(Thread. Buckle up! 👇🔥)
(Thread. Buckle up! 👇🔥)
If you were to include images in a Tweet that promoted progress specifically in GAN research (relativistic discriminators, wasserstein constraint, unrolled steps, spectral norm, etc.), it'd look like this... Not quite so catchy! 🤓 [2/8] 
It's like a different field of research.
The progress in the latest NVIDIA paper was made 100% with domain-specific changes independent of GANs. The authors say so themselves in the introduction: [3/8]
The progress in the latest NVIDIA paper was made 100% with domain-specific changes independent of GANs. The authors say so themselves in the introduction: [3/8]
Neural approaches to style transfer struggle with certain types of art, e.g. crisp yet smooth brush-strokes 🖋️. It's likely a combination of factors, including using models pre-trained on natural images. 📷
In this thread I'll experiment to learn more! 👇 #neuralimagen #procjam
In this thread I'll experiment to learn more! 👇 #neuralimagen #procjam
Ah. Here's what happens visually when the optimization algorithm (L-BFGS) "explodes" 💥. I have not tracked down the cause yet, likely extending #PyTorch to understand parameter ranges would help.
(Left: previous iteration looks OK, Right: pixels go far out of range → clamped)
(Left: previous iteration looks OK, Right: pixels go far out of range → clamped)
Example outputs of the Picasso drawing with more bias towards upper layers of the convnet (4x), then equalized, then bias towards lower layers (4x).
Interesting, but nothing like the original. Some insights forming!
Interesting, but nothing like the original. Some insights forming!
Computers cannot and will never be able to "be creative" — as judged by humans — entirely on their own. AI requires human-sourced examples, humans as evaluators, humans as instructors, humans as architects, humans providing intent...
The idea of "General Computational Creativity" is usually implemented as a clever combination of these human skills, with a fascinating goal to minimize human involvement. But so far all attempts have been well-branded machines that are products of their authors and environments.
This topic came up at the conference on computational creativity a couple weeks ago. There are clever ways to generate good explanations or motivations for creative bots, but they still felt fake to me... #ICCC18
