Facebook service describing a photo on Instagram
Vision

Every Picture Tells a Story

Facebook expanded a system of vision, language, and speech models designed to open the social network to users who are visually impaired. A Facebook service that describes photos in a synthesized voice now recognizes 1,200 visual concepts — 10 times more than the previous version.
2 min read
Data related to adversarial learning
Vision

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.
2 min read
Gun detecting system working and alerting the police
Vision

Draw a Gun, Trigger an Algorithm

Computer vision is alerting authorities the moment someone draws a gun. Several companies offer deep learning systems that enable surveillance cameras to spot firearms and quickly notify security guards or police.
1 min read
Rebag app working on a cellphone
Vision

How Much For That Vintage Gucci?

Computer vision is helping people resell their used designer handbags. Rebag, a resale company for luxury handbags, watches, and jewelry, launched Clair AI, an app that automatically appraises second-hand bags from brands like Gucci, Hermes, and Prada.
1 min read
AI-generated images with the model DALL-E
Vision

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.
2 min read
Covid Fast Fax operating
Vision

The Fax About Tracking Covid

A pair of neural networks is helping to prioritize Covid-19 cases for contact tracing. The public health department of California’s Contra Costa County is using deep learning to sort Covid-19 cases reported via the pre-internet technology known as fax.
2 min read
Tree farm dataset
Vision

Representing the Underrepresented

Some of deep learning’s bedrock datasets came under scrutiny as researchers combed them for built-in biases. Researchers found that popular datasets impart biases against socially marginalized groups to trained models due to the ways the datasets were compiled, labeled, and used.
2 min read
Robotaxi in different angles
Vision

Robotaxi Reimagined

A new breed of self-driving car could kick the autonomous-vehicle industry into a higher gear. Zoox unveiled its first product, an all-electric, driverless taxi designed fully in-house.
2 min read
Transkribus transcribing centuries-old letters and manuscripts
Vision

Written by Quill, Read by Computer

The secrets of history are locked in troves of handwritten documents. Now a machine learning platform is making them amenable to digital search. Transkribus is transcribing centuries-old records en masse and making them available to scholars worldwide.
1 min read
Video showing a Google app helping to keep a runner with impaired vision on track
Vision

Seeing Eye AI

A computer vision system is helping to keep runners with impaired vision on track.What’s new: A prototype smartphone app developed by Google translates camera images into audio signals.
2 min read
Fighter pilot in action
Vision

Phantom Menace

A fighter pilot battled a true-to-life virtual enemy in midair. In the skies over southern California, an airman pitted his dogfighting skills against an AI-controlled opponent that was projected onto his augmented-reality visor.
2 min read
Examples of contrastive learning
Vision

Learning From Words and Pictures

It’s expensive to pay doctors to label medical images, and the relative scarcity of high-quality training examples can make it hard for neural networks to learn features that make for accurate diagnoses.
2 min read
Example of a crowd size estimate
Vision

Better Crowd Counts

Did a million people attend the Million Man March? Estimates of the crowd size gathered at a given place and time can have significant political implications — and practical ones, too, as they can help public safety experts deploy resources for public health or crowd control.
2 min read
Face recognition system working on a bear
Vision

Caught Bearfaced

Many people worry that face recognition is intrusive, but wild animals seem to find it bearable. Melanie Clapham at University of Victoria with teammates of the BearID Project developed a model that performs face recognition for brown bears.
1 min read
Collage of self portraits
Vision

Unsupervised Prejudice

Social biases are well documented in decisions made by supervised models trained on ImageNet’s labels. But they also crept into the output of unsupervised models pretrained on the same dataset.
2 min read

Subscribe to The Batch

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