A group of drones flying over a field
Vision

Deadly Drones Act Alone

Autonomous weapons are often viewed as an alarming potential consequence of advances in AI — but they may already have been used in combat. Libyan forces unleashed armed drones capable of choosing their own targets against a breakaway rebel faction last year.
Architecture of vision-language tasks
Vision

One Model for Vision-Language

Researchers have proposed task-agnostic architectures for image classification tasks and language tasks. New work proposes a single architecture for vision-language tasks.
PimEyes working with pictures of Andrew Ng
Vision

Face Recognition for the Masses

Face recognition tech tends to be marketed to government agencies, but PimEyes offers a web app that lets anyone scan the internet for photos of themself — or anyone they have a picture of. The company says it aims to help people control their online presence and fight identity theft.
A new metod for compressing images and yielding better classification
Vision

What Machines Want to See

Researchers typically downsize images for vision networks to accommodate limited memory and accelerate processing. A new method not only compresses images but yields better classification.
FastNeRF accelerates the photorealistic 3D rendering method
Vision

Virtual Reality in Real Time

Ideally, real-time 3D applications such as virtual and augmented reality transition smoothly between different viewpoints of a scene — but generating a fresh perspective can take time. New research speeds the process.
Drones flying off the coast capturing video of orcas and models analyzing the imagery
Vision

Algorithms for Orcas

A combination of computer vision and drones could help restore dwindling killer whale populations. Researchers at Oregon State University and conservation groups SR3 and Vulcan developed a system that assesses the health of orcas.
Original vs processed image checking for leaks on a compressor
Vision

Super-Human Quality Control

A computer vision model, continually trained and automatically updated, can boost quality control in factories. Landing AI, a machine learning platform company led by Andrew Ng, helped a maker of compressors for refrigeration check them for leaks.
Series of videos showing AI-powered surveillance inside a bank
Vision

Banking on Computer Vision

AI-powered surveillance is becoming a staple in U.S. banks. Several banks are using cameras equipped with computer vision to bolster security and boost employee productivity, according to Reuters.
Tractable app determining the cost of a car's damage
Vision

Wreck Recognition

Automobile insurers are increasingly turning to machine learning models to calculate the cost of car repairs. The pandemic has made it difficult for human assessors to visit vehicles damaged in crashes, so the insurance industry is embracing automation.
Semantic Similarity Video Retrieval (SVR) working
Vision

Toward Better Video Search

Researchers at the University of Bristol led by Michael Wray propose a new benchmark, Semantic Similarity Video Retrieval (SVR), that evaluates video retrieval systems by their ability to rank many similar videos. They also built a system that performed well on it.
X-ray technique reproducing a painting that had been hidden beneath one of Pablo Picasso’s works
Vision

Crouching Beggar, Hidden Painting

Neural networks for image generation don’t just create new art — they can help recreate works that have been lost for ages. Oxia Palus, a UK startup dedicated to resurrecting lost art through AI.
Model identifying erroneous labels in popular datasets
Vision

Labeling Errors Everywhere

Key machine learning datasets are riddled with mistakes. Several benchmark datasets are shot through with incorrect labels. On average, 3.4 percent of examples in 10 commonly used datasets are mislabeled and the detrimental impact of such errors rises with model size.
Operators working with factory machinery
Vision

Who Watches the Welders?

A robot inspector is looking over the shoulders of robot welders. Farm equipment maker John Deere described a computer vision system that spots defective joints, helping to ensure that its heavy machinery leaves the production line ready to roll.
Blurred human faces in different pictures
Vision

De-Facing ImageNet

ImageNet now comes with privacy protection.What’s new: The team that manages the machine learning community’s go-to image dataset blurred all the human faces pictured in it and tested how models trained on the modified images on a variety of image recognition tasks.
Data related to SElf-supERvised (SEER), an image classifier pretrained on uncurated, unlabeled images
Vision

Pretraining on Uncurated Data

It’s well established that pretraining a model on a large dataset improves performance on fine-tuned tasks. In sufficient quantity and paired with a big model, even data scraped from the internet at random can contribute to the performance boost.

Subscribe to The Batch

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