Vision

241 Posts

Animation showing 3 main types of data augmentation and random cropping of a picture
Vision

Cookbook for Vision Transformers: A Formula for Training Vision Transformers

Vision Transformers (ViTs) are overtaking convolutional neural networks (CNN) in many vision tasks, but procedures for training them are still tailored for CNNs. New research investigated how various training ingredients affect ViT performance.
2 min read
Security camera behind barbed wire
Vision

Panopticon Down Under: Australian Prisons Adopt Face Recognition

A state in Australia plans to outfit prisons with face recognition. Corrective Services NSW, the government agency that operates nearly every prison in New South Wales, contracted the U.S.-based IT firm Unisys to replace a previous system.
2 min read
Animated overview of PP-Matting
Vision

Automating Mattes for Visual Effects: New ML Method Produces Image Mattes Easier

Researchers at Baidu introduced PP-Matting, an architecture that, given an image, estimates the transparency of pixels surrounding foreground objects to create mattes without requiring additional input.
3 min read
Capture of Honorlock, an AI-powered software designed to catch students who cheat on academic examinations
Vision

Court Blocks AI-Assisted Proctoring: AI Cheating Software Loses in Court

A U.S. court ruled against an implementation of AI-powered software designed to catch students who cheat on academic examinations.
2 min read
Illustration shows different self-attention mechanisms used by Transformer-based AI models.
Vision

Attention to Rows and Columns: Altering Transformers' Self-Attention Mechanism for Greater Efficiency

A new approach alters transformers' self-attention mechanism to balance computational efficiency with performance on vision tasks.
2 min read
Satellite imagery of suburban homes with backyard pools.
Vision

Spotting Tax Cheats From Overhead: French Authorities Use AI to Tax Pool Owners

French tax authorities netted nearly €10 million using an automated system to identify unregistered pools
1 min read
Object-Detection Transformers Simplified: New Research Improves Object Detection With Vision Transformers
Vision

Object-Detection Transformers Simplified: New Research Improves Object Detection With Vision Transformers

ViTDet, a new system from Facebook, adds an object detector to a plain pretrained transformer.
2 min read
Fishermen insert their catch into a machine from Shinkei Systems, which automatically processes the fish.
Vision

Neural Nets Catch Fresher Fish: Robot Deck Hand Automatically Processes Fish

Shinkei Systems developed a machine that uses computer vision to slaughter fish in a way that maximizes their shelf life and flavor.
1 min read
Animated chart shows how AI can avoid mistaking an image's subject for its context.
Vision

Taming Spurious Correlations: New Technique Helps AI Avoid Classification Mistakes

When a neural network learns image labels, it may confuse a background item for the labeled object. New research avoids such mistakes.
2 min read
An animation shows an AI-powered system called From Numbers to Names, which identifies Holocaust victims in photographs.
Vision

Identifying Faces of History: From Numbers to Names Uses AI to Identify Holocaust Victims

From Numbers to Names matches individuals to faces in publicly available images related to the genocide of European Jews between 1941 and 1945.
2 min read
EU badge in a vehicle's hood
Vision

Keep Your AIs on the Road: New Law Requires European Vehicles to Come with Automated Features

The European Union passed a law that requires new vehicles to come equipped with automated safety features.
2 min read
A series of graphs show the carbon emissions associated with training AI models.
Vision

Cutting the Carbon Cost of Training: A New Tool Helps AI Developers Lower Their Greenhouse Gas Emissions

You can reduce your model’s carbon emissions by being choosy about when and where you train it.
2 min read
Two randomly cropped pictures
Vision

Tradeoffs for Higher Accuracy

Vision models can be improved by training them on several altered versions of the same image and also by encouraging their weights to be close to zero. Recent research showed that both can have adverse effects that may be difficult to detect.
2 min read
Autonomous research ship in the ocean
Vision

AI AI, Captain!

An autonomous research ship crossed the Atlantic Ocean — with a few pit stops to address challenges along the way. Built by IBM and marine research nonprofit ProMare, the Mayflower Autonomous Ship 400 (MAS400) last week completed a voyage from Plymouth, England, to Plymouth, Massachusetts.
2 min read
Satalite Map image
Vision

Tracking Changes on Earth’s Surface

Computer vision systems are scanning satellite photos to track construction on the Earth’s surface — an exercise in behavior recognition on a global scale.
3 min read

Subscribe to The Batch

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