Images and graphs related to Dense Steerable Filter CNN (DSF-CNN)
Vision

Seeing Straight at Any Rotation

A cat rotated by any number of degrees is still a cat. It takes a lot of rotated training images to teach convolutional filters this simple fact. A new filter design has this common-sense knowledge built-in.
2 min read
Operation of a virtual fitting room
Vision

Clothes Make the Model

In online retailing, the most common customer complaints are slow shipping and inability to try on clothes. Amazon conceived its Prime program to address the first concern. To answer the second, it built a virtual fitting room.
2 min read
Neural network tracking the body position of chimpanzees
Vision

Model See, Model Do

Scientists who study animal behavior spend endless hours observing and taking notes about a creature’s actions and reactions. Computer vision could automate much of that work.
1 min read
Excerpt from study about models that learn to predict task-specific distance metrics
Vision

Misleading Metrics

A growing body of literature shows that some steps in AI’s forward march may actually move sideways. A new study questions advances in metric learning.
2 min read
Illustration of a broken heart with a smirk in the middle
Vision

Outing Hidden Hatred

Facebook uses automated systems to block hate speech, but hateful posts can slip through when seemingly benign words and pictures combine to create a nasty message. The social network is tackling this problem by enhancing AI’s ability to recognize context.
2 min read
Face recognition system working on people wearing masks
Vision

Who Was That Masked Protester?

Vendors of face recognition are updating their tech as people don masks to protect against Covid-19. Police are bound to take notice. Companies that provide computer vision systems, including at least one that supplies law enforcement agencies, are training models to recognize obscured faces.
2 min read
Data and graphs related to a method that synthesizes extracted features of underrepresented classes
Vision

Augmentation for Features

In any training dataset, some classes may have relatively few examples. A new technique can improve a trained model’s performance on such underrepresented classes. Researchers introduced a method that synthesizes extracted features of underrepresented classes.
2 min read
Dishwashing robot working
Vision

AI Does the Dishes

A pioneer in dishwashing robots is reaching into commercial kitchens. Dishcraft Robotics uses machines equipped with computer vision to scrub dirties for corporate food services and, soon, restaurants.
1 min read
Data related to YOLOv4
Vision

Another Look at YOLO

The latest update of the acclaimed real-time object detector You Only Look Once is more accurate than ever. Researchers at Taiwan’s Institute of Information Science Academia Sinica offer YOLOv4 — the first version not to include the architecture’s original creators.
2 min read
Animated drawing of hardware related to AI
Vision

Horsepower for Next-Gen Networks

The for-profit research organization OpenAI has a new supercomputer to help achieve its dream of building the world’s most sophisticated AI. Microsoft engineered the new hardware network to train immense models on thousands of images, texts, and videos simultaneously.
1 min read
Data related to few-shot learning
Vision

Small Data the Simple Way

Few-shot learning seeks to build models that adapt to novel tasks based on small numbers of training examples. This sort of learning typically involves complicated techniques, but researchers achieved state-of-the-art results using a simpler approach.
2 min read
Information and examples of CheXbert, a network that labels chest X-rays
Vision

Human-Level X-Ray Diagnosis

Like nurses who can’t decipher a doctor’s handwriting, machine learning models can’t decipher medical scans — without labels. Conveniently, natural language models can read medical records to extract labels for X-ray images.
2 min read
False information about Covid-19 on Facebook posts
Vision

Information Warfare: Covid Edition

Facebook’s AI can’t spot Covid-19 disinformation on its own. But with human help, it can slow the spread. Facebook uses a combination of humans and neural nets to crack down on messages that make false claims about Covid-19, which may have deadly consequences.
1 min read
Face recognition system identifying a person wearing a mask
Vision

Mask Monitor

Cameras that detect face masks are helping French authorities to evaluate citizens’ adherence to government mandates intended to fight Covid-19. Starting this week, everyone riding public transportation in France is required to wear a face mask.
1 min read
Excerpts from Newspaper Navigator
Vision

An Archive Unearthed

An algorithm indexed photos, ads, and other images embedded in 170 years of American newspapers. Created by researchers at the University of Washington and U.S. Library of Congress, Newspaper Navigator uses object recognition to organize visual features of newspapers dating back to 1789.
1 min read

Subscribe to The Batch

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