Eyes on the Prize: Vision-only reinforcement learning improves generalizability.
Vision

Eyes on the Prize: Vision-only reinforcement learning improves generalizability.

When the chips are down, humans can track critical details without being distracted by irrelevancies. New research helps reinforcement learning models similarly focus on the most important details.

July 29, 20202 min read
Grade-AI Sushi: How Tuna Scope assesses the quality of sushi-grade fish
Vision

Grade-AI Sushi: How Tuna Scope assesses the quality of sushi-grade fish

Computer vision is helping sushi lovers enjoy top-quality maguro. Japanese restaurant chain Kura Sushi is using a smartphone app called Tuna Scope to grade its suppliers’ offerings, according to the news outlet The Asahi Shimbun.

July 29, 20201 min read
Grade-AI Sushi: How Tuna Scope assesses the quality of sushi-grade fish
Vision

Grade-AI Sushi: How Tuna Scope assesses the quality of sushi-grade fish

Computer vision is helping sushi lovers enjoy top-quality maguro. Japanese restaurant chain Kura Sushi is using a smartphone app called Tuna Scope to grade its suppliers’ offerings, according to the news outlet The Asahi Shimbun.

July 29, 20201 min read
AI Against Covid Progress Report: How Chinese authorities used AI to fight Covid
Vision

AI Against Covid Progress Report: How Chinese authorities used AI to fight Covid

A new report details the role of AI in China’s effort to fight the coronavirus. Researchers at Synced, a China-based AI publication, describe how nearly 90 machine learning products have contributed to the country’s pandemic response.

July 29, 20201 min read
Eyes on the Prize: Vision-only reinforcement learning improves generalizability.
Vision

Eyes on the Prize: Vision-only reinforcement learning improves generalizability.

When the chips are down, humans can track critical details without being distracted by irrelevancies. New research helps reinforcement learning models similarly focus on the most important details.

July 29, 20202 min read
Less (Video) is More (Examples): A small data AI tool for classifying video
Vision

Less (Video) is More (Examples): A small data AI tool for classifying video

We’d all love to be able to find similar examples of our favorite cat videos. But few of us want to label thousands of similar videos of even the cutest kitties. New research makes headway in video classification when training examples are scarce.

July 29, 20202 min read
Which Shoes Go With That Outfit?: An AI with fashion sense assembles outfits.
Vision

Which Shoes Go With That Outfit?: An AI with fashion sense assembles outfits.

Need a wardrobe upgrade? You could ask the fashion mavens at Netflix’s Queer Eye — or you could use a new neural network. Researchers at Amazon propose Category-based Subspace Attention Network (CSA-Net) to predict and retrieve compatible garments and accessories that complement one another.

July 22, 20202 min read
Which Shoes Go With That Outfit?: An AI with fashion sense assembles outfits.
Vision

Which Shoes Go With That Outfit?: An AI with fashion sense assembles outfits.

Need a wardrobe upgrade? You could ask the fashion mavens at Netflix’s Queer Eye — or you could use a new neural network. Researchers at Amazon propose Category-based Subspace Attention Network (CSA-Net) to predict and retrieve compatible garments and accessories that complement one another.

July 22, 20202 min read
Assembly Line AI: How companies are using AI to spot manufacturing flaws
Vision

Assembly Line AI: How companies are using AI to spot manufacturing flaws

Computer vision has been learning how to spot manufacturing flaws. The pandemic is accelerating that education. Companies like Instrumental and Elementary are making AI-powered cameras that automate the spotting of damaged or badly assembled products on factory assembly lines.

July 15, 20201 min read
That Online Boutique, But Smarter: A summary of Amazon's Visiolinguistic Attention Learning
Vision

That Online Boutique, But Smarter: A summary of Amazon's Visiolinguistic Attention Learning

Why search for “a cotton dress shirt with button-down collar, breast pockets, barrel cuffs, scooped hem, and tortoise shell buttons in grey” when a photo and the words “that shirt, but grey” will do the trick? A new network understands the image-text combo.

July 15, 20202 min read
Assembly Line AI: How companies are using AI to spot manufacturing flaws
Vision

Assembly Line AI: How companies are using AI to spot manufacturing flaws

Computer vision has been learning how to spot manufacturing flaws. The pandemic is accelerating that education. Companies like Instrumental and Elementary are making AI-powered cameras that automate the spotting of damaged or badly assembled products on factory assembly lines.

July 15, 20201 min read
That Online Boutique, But Smarter: A summary of Amazon's Visiolinguistic Attention Learning
Vision

That Online Boutique, But Smarter: A summary of Amazon's Visiolinguistic Attention Learning

Why search for “a cotton dress shirt with button-down collar, breast pockets, barrel cuffs, scooped hem, and tortoise shell buttons in grey” when a photo and the words “that shirt, but grey” will do the trick? A new network understands the image-text combo.

July 15, 20202 min read
Seeing Straight at Any Rotation: Dense Steerable Filter CNN (DSF-CNN) identifies rotated images.
Vision

Seeing Straight at Any Rotation: Dense Steerable Filter CNN (DSF-CNN) identifies rotated images.

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.

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
Seeing Straight at Any Rotation: Dense Steerable Filter CNN (DSF-CNN) identifies rotated images.
Vision

Seeing Straight at Any Rotation: Dense Steerable Filter CNN (DSF-CNN) identifies rotated images.

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.

July 8, 20202 min read

Subscribe to The Batch

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