Computer Vision Transformed: Google's Detection Transformer (DETR) for object detection
Vision

Computer Vision Transformed: Google's Detection Transformer (DETR) for object detection

The transformer architecture that has shaken up natural language processing may replace recurrent layers in object detection networks. A Facebook team led by Nicolas Carion and Francisco Massa simplified object detection pipelines by using transformers, yielding Detection Transformer (DETR).

July 8, 20201 min read
Computer Vision Transformed: Google's Detection Transformer (DETR) for object detection
Vision

Computer Vision Transformed: Google's Detection Transformer (DETR) for object detection

The transformer architecture that has shaken up natural language processing may replace recurrent layers in object detection networks. A Facebook team led by Nicolas Carion and Francisco Massa simplified object detection pipelines by using transformers, yielding Detection Transformer (DETR).

July 8, 20201 min read
Tiny Images, Outsized Biases: Why MIT withdrew the Tiny Images dataset
Vision

Tiny Images, Outsized Biases: Why MIT withdrew the Tiny Images dataset

MIT withdrew a popular computer vision dataset after researchers found that it was rife with social bias. Researchers found racist, misogynistic, and demeaning labels among the nearly 80 million pictures in Tiny Images, a collection of 32-by-32 pixel color photos.

July 8, 20202 min read
Game Changer: Top football clubs are using AI to improve performance.
Vision

Game Changer: Top football clubs are using AI to improve performance.

Football clubs are turning to computer vision for winning insights. Acronis, a Swiss cloud storage and security company, offers AI services designed to give a boost to some of the world’s top football clubs (soccer teams, to Americans), Wired reported.

July 8, 20201 min read
Tiny Images, Outsized Biases: Why MIT withdrew the Tiny Images dataset
Vision

Tiny Images, Outsized Biases: Why MIT withdrew the Tiny Images dataset

MIT withdrew a popular computer vision dataset after researchers found that it was rife with social bias. Researchers found racist, misogynistic, and demeaning labels among the nearly 80 million pictures in Tiny Images, a collection of 32-by-32 pixel color photos.

July 8, 20202 min read
Model See, Model Do: Researchers use DensePose to analyze animal behavior.
Vision

Model See, Model Do: Researchers use DensePose to analyze animal behavior.

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.

July 1, 20201 min read
Model See, Model Do: Researchers use DensePose to analyze animal behavior.
Vision

Model See, Model Do: Researchers use DensePose to analyze animal behavior.

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.

July 1, 20201 min read
Clothes Make the Model: Amazon's Outfit-Viton generates apparel images on demand.
Vision

Clothes Make the Model: Amazon's Outfit-Viton generates apparel images on demand.

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.

July 1, 20202 min read
Clothes Make the Model: Amazon's Outfit-Viton generates apparel images on demand.
Vision

Clothes Make the Model: Amazon's Outfit-Viton generates apparel images on demand.

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.

July 1, 20202 min read
Misleading Metrics: Advances in metric learning may be illusions.
Vision

Misleading Metrics: Advances in metric learning may be illusions.

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.

June 24, 20202 min read
Misleading Metrics: Advances in metric learning may be illusions.
Vision

Misleading Metrics: Advances in metric learning may be illusions.

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.

June 24, 20202 min read
Outing Hidden Hatred: How Facebook built a hate speech detector
Vision

Outing Hidden Hatred: How Facebook built a hate speech detector

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.

June 17, 20202 min read
Outing Hidden Hatred: How Facebook built a hate speech detector
Vision

Outing Hidden Hatred: How Facebook built a hate speech detector

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.

June 17, 20202 min read
Who Was That Masked Protester?: Some face recognition can identify people in masks.
Vision

Who Was That Masked Protester?: Some face recognition can identify people in masks.

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.

June 10, 20202 min read
Who Was That Masked Protester?: Some face recognition can identify people in masks.
Vision

Who Was That Masked Protester?: Some face recognition can identify people in masks.

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.

June 10, 20202 min read

Subscribe to The Batch

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