Nav: Home

New AI computer vision system mimics how humans visualize and identify objects

December 20, 2018

Researchers from UCLA Samueli School of Engineering and Stanford have demonstrated a computer system that can discover and identify the real-world objects it "sees" based on the same method of visual learning that humans use.

The system is an advance in a type of technology called "computer vision," which enables computers to read and identify visual images. It is an important step toward general artificial intelligence systems--computers that learn on their own, are intuitive, make decisions based on reasoning and interact with humans in a more human-like way. Although current AI computer vision systems are increasingly powerful and capable, they are task-specific, meaning their ability to identify what they see is limited by how much they have been trained and programmed by humans.

Even today's best computer vision systems cannot create a full picture of an object after seeing only certain parts of it--and the systems can be fooled by viewing the object in an unfamiliar setting. Engineers are aiming to make computer systems with those abilities--just like humans can understand that they are looking at a dog, even if the animal is hiding behind a chair and only the paws and tail are visible. Humans, of course, can also easily intuit where the dog's head and the rest of its body are, but that ability still eludes most artificial intelligence systems.

Current computer vision systems are not designed to learn on their own. They must be trained on exactly what to learn, usually by reviewing thousands of images in which the objects they are trying to identify are labeled for them.

Computers, of course, also cannot explain their rationale for determining what the object in a photo represents: AI-based systems do not build an internal picture or a common-sense model of learned objects the way humans do.

The engineers' new method, described in the Proceedings of the National Academy of Sciences, shows a way around these shortcomings.

The approach is made up of three broad steps. First, the system breaks up an image into small chunks, which the researchers call "viewlets." Second, the computer learns how these viewlets fit together to form the object in question. And finally, it looks at what other objects are in the surrounding area, and whether or not information about those objects is relevant to describing and identifying the primary object.

To help the new system "learn" more like humans, the engineers decided to immerse it in an internet replica of the environment humans live in.

"Fortunately, the internet provides two things that help a brain-inspired computer vision system learn the same way humans do," said Vwani Roychowdhury, a UCLA professor of electrical and computer engineering and the study's principal investigator. "One is a wealth of images and videos that depict the same types of objects. The second is that these objects are shown from many perspectives--obscured, bird's eye, up-close--and they are placed in different kinds of environments."

To develop the framework, the researchers drew insights from cognitive psychology and neuroscience.

"Starting as infants, we learn what something is because we see many examples of it, in many contexts," Roychowdhury said. "That contextual learning is a key feature of our brains, and it helps us build robust models of objects that are part of an integrated worldview where everything is functionally connected."

The researchers tested the system with about 9,000 images, each showing people and other objects. The platform was able to build a detailed model of the human body without external guidance and without the images being labeled.

The engineers ran similar tests using images of motorcycles, cars and airplanes. In all cases, their system performed better or at least as well as traditional computer vision systems that have been developed with many years of training.
-end-
The study's co-senior author is Thomas Kailath, a professor emeritus of electrical engineering at Stanford who was Roychowdhury's doctoral advisor in the 1980s. Other authors are former UCLA doctoral students Lichao Chen (now a research engineer at Google) and Sudhir Singh (who founded a company that builds robotic teaching companions for children).

Singh, Roychowdhury and Kailath previously worked together to develop one of the first automated visual search engines for fashion, the now-shuttered StileEye, which gave rise to some of the basic ideas behind the new research.

UCLA Samueli School of Engineering

Related Engineering Articles:

Engineering the meniscus
Damage to the meniscus is common, but there remains an unmet need for improved restorative therapies that can overcome poor healing in the avascular regions.
Artificially engineering the intestine
Short bowel syndrome is a debilitating condition with few treatment options, and these treatments have limited efficacy.
Reverse engineering the fireworks of life
An interdisciplinary team of Princeton researchers has successfully reverse engineered the components and sequence of events that lead to microtubule branching.
New method for engineering metabolic pathways
Two approaches provide a faster way to create enzymes and analyze their reactions, leading to the design of more complex molecules.
Engineering for high-speed devices
A research team from the University of Delaware has developed cutting-edge technology for photonics devices that could enable faster communications between phones and computers.
Breakthrough in blood vessel engineering
Growing functional blood vessel networks is no easy task. Previously, other groups have made networks that span millimeters in size.
Next-gen batteries possible with new engineering approach
Dramatically longer-lasting, faster-charging and safer lithium metal batteries may be possible, according to Penn State research, recently published in Nature Energy.
What can snakes teach us about engineering friction?
If you want to know how to make a sneaker with better traction, just ask a snake.
Engineering a plastic-eating enzyme
Scientists have engineered an enzyme which can digest some of our most commonly polluting plastics, providing a potential solution to one of the world's biggest environmental problems.
A new way to do metabolic engineering
University of Illinois researchers have created a novel metabolic engineering method that combines transcriptional activation, transcriptional interference, and gene deletion, and executes them simultaneously, making the process faster and easier.
More Engineering News and Engineering Current Events

Top Science Podcasts

We have hand picked the top science podcasts of 2019.
Now Playing: TED Radio Hour

In & Out Of Love
We think of love as a mysterious, unknowable force. Something that happens to us. But what if we could control it? This hour, TED speakers on whether we can decide to fall in — and out of — love. Guests include writer Mandy Len Catron, biological anthropologist Helen Fisher, musician Dessa, One Love CEO Katie Hood, and psychologist Guy Winch.
Now Playing: Science for the People

#543 Give a Nerd a Gift
Yup, you guessed it... it's Science for the People's annual holiday episode that helps you figure out what sciency books and gifts to get that special nerd on your list. Or maybe you're looking to build up your reading list for the holiday break and a geeky Christmas sweater to wear to an upcoming party. Returning are pop-science power-readers John Dupuis and Joanne Manaster to dish on the best science books they read this past year. And Rachelle Saunders and Bethany Brookshire squee in delight over some truly delightful science-themed non-book objects for those whose bookshelves are already full. Since...
Now Playing: Radiolab

An Announcement from Radiolab