Tag-Retrieve-Compose-Synthesize (TReCS)
Generative Adversarial Network (GAN)

Pictures From Words and Gestures

A new system combines verbal descriptions and crude lines to visualize complex scenes. Google researchers led by Jing Yu Koh proposed Tag-Retrieve-Compose-Synthesize (TReCS), a system that generates photorealistic images by describing what they want to see while mousing around on a blank screen.
Images generated by a network designed to visualize what goes on in peoples’ brains while they watch Doctor Who
Generative Adversarial Network (GAN)

What the Brain Sees

What’s creepier than images from the sci-fi TV series Doctor Who? Images generated by a network designed to visualize what goes on in peoples’ brains while they watch Doctor Who.
Examples of images being produced from noise
Generative Adversarial Network (GAN)

Images From Noise

Generative adversarial networks and souped-up language models aren’t the only image generators around. Researchers recently upgraded an alternative known as score-based generative models.
Data related to adversarial learning
Generative Adversarial Network (GAN)

Adversarial Helper

Models that learn relationships between images and words are gaining a higher profile. New research shows that adversarial learning, usually a way to make models robust to deliberately misleading inputs, can boost vision-and-language performance.
AI-generated images with the model DALL-E
Generative Adversarial Network (GAN)

Tell Me a Picture

Two new models show a surprisingly sharp sense of the relationship between words and images. OpenAI, the for-profit research lab, announced a pair of models that have produced impressive results in multimodal learning: DALL·E.
Dozens of snowmen with different characteristics
Generative Adversarial Network (GAN)

This Snowman Does Not Exist

While generative adversarial networks were infiltrating cultural, social, and scientific spheres, they quietly transformed the web into a bottomless well of synthetic images of . . . well, you name it.
Examples of Xpression app working (people in pajamas looking like they're wearing suits)
Generative Adversarial Network (GAN)

GAN Makes Pajamas Safe For Work

A new camera app uses a generative adversarial network to let users look like they’re dressed for success while they videoconference in their jammies. Xpression is an iPhone app that maps facial expressions onto till images in real time, allowing users to look clothed in digital costumes.
Graphs showing how DeepRhythm detects deepfakes
Generative Adversarial Network (GAN)

Deepfakes Are Heartless

The incessant rhythm of a heartbeat could be the key to distinguishing real videos from deepfakes. DeepRhythm detects deepfakes using an approach inspired by the science of measuring minute changes on the skin’s surface due to blood circulation.
Graphs and examples of Network dissection technique
Generative Adversarial Network (GAN)

What One Neuron Knows

How does a convolutional neural network recognize a photo of a ski resort? New research shows that it bases its classification on specific neurons that recognize snow, mountains, trees, and houses.
Series of images showing how Maxine, a media streaming platform, works
Generative Adversarial Network (GAN)

Data Compression By AI

In this work-from-home era, who hasn’t spent a video conference wishing they could read an onscreen document without turning their eyes from the person they’re talking with? Or simply hoping the stream wouldn’t stutter or stall? Deep learning can fill in the missing pieces.
Examples of AI generated images
Generative Adversarial Network (GAN)

GANs for Smaller Data

Trained on a small dataset, generative adversarial networks (GANs) tend to generate either replicas of the training data or noisy output. A new method spurs them to produce satisfying variations.
Excerpts of HBO documentary "Welcome to Chechnya"
Generative Adversarial Network (GAN)

Protected By Deepfakes

Documentary filmmakers often shield the identities of people who might be harmed for speaking out. But typical tactics like blurring faces and distorting voices can make it hard for audiences to connect emotionally. A new
Data and examples related to a new technique to detect portions of an image
Generative Adversarial Network (GAN)

The Telltale Artifact

Deepfakes have gone mainstream, allowing celebrities to star in commercials without setting foot in a film studio. A new method helps determine whether such endorsements — and other images produced by generative adversarial networks — are authentic.
Makeup applied on female faces with the help of augmented reality
Generative Adversarial Network (GAN)

A Good Look for AI

Trying on new makeup is a hassle — apply, inspect, wash off, repeat. Not to mention the tribulation of visiting brick-and-mortar stores during the pandemic. Augmented reality is helping people try on all the makeup they want without leaving home.
Data and examples related to IMLE-GAN
Generative Adversarial Network (GAN)

Making GANs More Inclusive

A typical GAN’s output doesn’t necessarily reflect the data distribution of its training set. Instead, GANs are prone to modeling the majority of the training distribution, sometimes ignoring rare attributes — say, faces that represent minority populations.

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox