New artificial intelligence system mimics how humans visualize and identify objects

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.

Dec 18, 2018 - By UCLA Samueli Newsroom

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.”

Photo: The “computer vision” system can identify objects based on only partial glimpses, like by using these photo snippets of a motorcycle. (credits: UCLA Samueli School of Engineering / Stanford)

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.

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.

Read more

Comments

No comments to display.

Related posts

Hadron Therapy Industry 2019-2025: Global Size, Share, Emerging Trends, Demand, Revenue and Forecasts Research

Hadron Therapy Industry 2019 Global Market research report studies latest Hadron Therapy industry aspects market size, share, trends, growth, business overview and Hadron Therapy industry scenario during the forecast period (2019-2025).

Acid Catalysts Industry 2019: Global Market Size, Growth, Share, Insights, Supply, Drivers, Demand, Outlook, Trends and Forecasts 2025

A latest report has been added to the wide database of Orian Research Consultant titled “Global Acid Catalysts Market Research Report (2025)” which provides an outlook of current market value, Size, Share, Growth, Trends and Forecast.
3 days ago

Continuous Renal Replacement Therapy Industry 2019 Global Market Size, Share, Growth, Sales and Drivers Analysis Research Report 2025

Continuous Renal Replacement Therapy Industry 2019 Global Market Research report provides information regarding market size, share, trends, growth, cost structure, capacity, and revenue and forecast 2025.

Black Pellets Industry 2019 Global Market Size, Outlook, Demand, Key Manufacturers and 2025 Forecast

A recent market report published on the “Black Pellets Industry” presents an in-depth overview of the Black Pellets industry. Global Black Pellets market research report covers the overview, summary, Black Pellets market dynamics, competitive analysis, and leading player’s various strategies to sustain in the global market. Apart from this, the Black Pellets report also covers detail information about various clients which is the most significant element for the manufacturers.
3 days ago

Call for Applications: Startup World Cup 2019

Startup World Cup ("SWC") offers innovation and entrepreneurship opportunities for startup ecosystems around the world. This platform consists of a global series of startup conferences and competitions that bring together phenomenal startups, VCs, and world-class tech CEOs.
Application Deadline in 2 months

EU Call for Proposals: Information and promotion about the sustainable aspect of rice production

The objective is to highlight the sustainable aspect of rice sector. Rice production in Europe has a particular environmental dimension, being at the heart of the preservation of certain wetlands. Rice cultivation is a sensitive and specific practice at European level, since it is produced in areas where there are few crop alternatives. Its preservation and improvement contribute to the sustainability of rice producing regions, by playing an active role in maintaining rural areas, protecting nature and preserving biodiversity. Actions shall highlight the environmental sustainability of the production, stressing its beneficial role for climate action and the environment.
Application Deadline in 22 days

A low-cost and open-source platform for automated imaging

Remote monitoring of plants using hyperspectral imaging has become an important tool for the study of plant growth, development, and physiology. Many applications are oriented towards use in field environments to enable non-destructive analysis of crop responses due to factors such as drought, nutrient deficiency, and disease, e.g., using tram, drone, or airplane mounted instruments.

Can developing nations compete in a digital world?

People want in on e-commerce for simple reasons - choice, ease, speed, cost, convenience. Yet not everyone benefits equally, especially in least developed countries.