TransGAN: Two Transformers Can Make One Strong GAN

Recommendable! This could be a breakthrough!

"The recent explosive interest on transformers has suggested their potential to become powerful “universal” models for computer vision tasks, such as classification, detection, and segmentation. However, how further transformers can go - are they ready to take some more notoriously difficult vision tasks, e.g., generative adversarial networks (GANs)? Driven by that curiosity, we conduct the first pilot study in building a GAN completely free of convolutions, using only pure transformer-based architectures. ..."

[2102.07074] TransGAN: Two Transformers Can Make One Strong GAN

Visualizing the world beyond the frame

Getting computer vision ready to dream! :-)



"An open secret in contemporary machine learning is that many models work beautifully on standard benchmarks but fail to generalize outside the lab. ... Generative models are no exception, but recent advances in generative adversarial networks (GANs) suggest otherwise – these models can now synthesize strikingly realistic and diverse images. ..."



Visualizing the world beyond the frame | MIT News Researchers test how far artificial intelligence models can go in dreaming up varied poses and colors of objects and animals in photos.

Giant Pandas In Love And What It Sounds Like

Andrew Ng, a renowned AI researcher, reports in his latest The Batch newsletter (2/12/2020):
"What Love Sounds Like
Female giant pandas are fertile for only 24 to 36 hours a year: Valentine’s Day on steroids. A new neural network alerts human keepers when a panda couple mates.

What’s new: Panda breeders are struggling to lift the creatures' global population, and tracking success in mating helps maintain their numbers. WeiRan Yan of Sichuan University, with researchers from Chengdu Research Base of Giant Panda Breeding and Sichuan Academy of Giant Panda, developed CGANet, a speech recognition network that flags consummated unions based on panda vocalizations.
Key insight: Prior work discovered the relationship between panda calls and mating success. A preliminary model used hand-crafted features to recognize calls meaning, “Wow, honey, you were great!” CGANet uses features extracted through deep learning.
How it works: The researchers trained CGANet on recordings of pandas during mating season labeled for mating success.
The model divides each recorded call into pieces and computes a frequency representation of each piece.
It uses convolutional, recurrent, and attention layers in turn to find patterns that predict mating success in different aspects of the pieces and their interrelationships. 
It computes the probability of mating success for each piece, then sums the probabilities to generate a prediction for the call as a whole.
Results: CGANet’s predictions were 89.9 percent accurate, a new state of the art compared with the earlier model’s 84.5 percent. CGANet also substantially improved AUC (area under curve, a measure of true versus false positives).

Why it matters: Tracking a panda’s love life once required obtaining its hormones — a difficult and time-consuming feat. CGANet allows real-time, non-invasive prediction so keepers can give the less popular pandas another chance while they’re still fertile.

We’re thinking: For pandas, a happy Valentine’s Day is essential to perpetuate the species. Tools like CGANet could help save these unique creatures from extinction."

Not to be trifled with, this is serious academic AI research using state of the art generative adversarial networks (GAN):
Audio-based automatic mating success prediction of giant pandas

What the AI researchers may have overlooked here is what sounds does a female giant panda make when she is ready?

The Batch: Hotter Dating Profiles, Pandas in Love, Compute for Coronavirus, Deepfake Detection, Self-Driving Cars Run Amok: