Invariance And Computer Vision

In work that could lead to much-improved computer vision systems, Massachusetts Institute of Technology (MIT) neuroscientists have tricked the visual cortex into confusing one object with another, thereby demonstrating that time teaches us how to recognize objects.

Because an object such as a cat can produce innumerable different impressions on the retina – depending on the direction of gaze, angle of view, distance and so forth – our eyes never see the same image twice. Yet our perception of the cat remains stable, an attribute of our visual system known as “invariance.”

“This invariance is fundamental to our ability to recognize objects – it feels effortless, but it is a central challenge for computational neuroscience,” explained James DiCarlo, the senior author of the new study. “We want to understand how our brains acquire invariance and how we might incorporate it into computer vision systems.”

One hypothesis is that our eyes tend to move rapidly (about three times per second), whereas physical objects usually change more slowly. Therefore, differing patterns of activity in rapid succession often reflect different images of the same object. Could the brain take advantage of this simple rule of thumb to learn object invariance?

In previous work, DiCarlo tested this “temporal contiguity” idea in humans by creating an altered visual world in which the normal rule did not apply. An object would appear in peripheral vision, but as the eyes moved to examine it, the object would be swapped for a different object. Although the subjects did not perceive the change, they soon began to confuse the two objects, consistent with the temporal contiguity hypothesis.

In the new study, DiCarlo had monkeys watch a similarly altered world while recording from neurons in the inferior temporal (IT) cortex – a high-level visual brain area where object invariance is thought to arise. IT neurons “prefer” certain objects and respond to them regardless of where they appear within the visual field.

“We first identified an object that an IT neuron preferred, such as a sailboat, and another, less preferred object, maybe a teacup,” co-researcher Nuo Li explained. “When we presented objects at different locations in the monkey’s peripheral vision, they would naturally move their eyes there. One location was a swap location. If a sailboat appeared there, it suddenly became a teacup by the time the eyes moved there. But a sailboat appearing in other locations remained unchanged.”

After the monkeys spent time in this altered world, their IT neurons became confused, just like the previous human subjects. The sailboat neuron, for example, still preferred sailboats at all locations – except at the swap location, where it learned to prefer teacups. The longer the manipulation, the greater the confusion, exactly as predicted by the temporal contiguity hypothesis.

Importantly, just as human infants can learn to see without adult supervision, the monkeys received no feedback from the researchers. Instead, the changes in their brain occurred spontaneously as the monkeys looked freely around the computer screen. “We were surprised by the strength of this neuronal learning, especially after only one or two hours of exposure,” DiCarlo told the journal Science. “Even in adulthood, it seems that the object-recognition system is constantly being retrained by natural experience. Considering that a person makes about 100 million eye movements per year, this mechanism could be fundamental to how we recognize objects so easily.”

Related:
Context And Computer Vision
Computer Recognizes Attractiveness In Women
Qualia

Source: McGovern Institute for Brain Research, Massachusetts Institute of Technology

, ,

Comments are closed.

1993 Skull and Brain Polaroid Future Vision Hologram Sticker Sealed Card RARE picture

1993 Skull and Brain Polaroid Future Vision Hologram Sticker Sealed Card RARE

$42.49



Saint Nicholas computer square ornament Xmas holiday tree picture

Saint Nicholas computer square ornament Xmas holiday tree

$12.75



Captain America Epic Collection: The Bloodstone Hunt (Epic Collection Cap - GOOD picture

Captain America Epic Collection: The Bloodstone Hunt (Epic Collection Cap - GOOD

$159.98



1981 2-page Apple Computer Ad - Improves Vision picture

1981 2-page Apple Computer Ad - Improves Vision

$16.99



OVERPOWER Vision SET 2 hero IQ 8 sp Compute Victory Intangible Strike +1 bonus picture

OVERPOWER Vision SET 2 hero IQ 8 sp Compute Victory Intangible Strike +1 bonus

$14.49



Computer Vision -- circa 1979, Dick Zimmerman close up mentalism fooler    TMGS picture

Computer Vision -- circa 1979, Dick Zimmerman close up mentalism fooler TMGS

$26.99



1982 Ardan Store Christmas Catalog Coleco Vision Texas Instruments Computer Toys picture

1982 Ardan Store Christmas Catalog Coleco Vision Texas Instruments Computer Toys

$24.99



1981 Apple Personal Computer: Reddy Chirra Improves His Vision Vintage Print Ad picture

1981 Apple Personal Computer: Reddy Chirra Improves His Vision Vintage Print Ad

$6.50



Photo 6x4 Vision Computer Centre, Abergavenny Town centre computer shop a c2016 picture

Photo 6x4 Vision Computer Centre, Abergavenny Town centre computer shop a c2016

$2.38



Photo 6x4 Vision Computer Centre, 24 Cross Street, Abergavenny Next door  c2018 picture

Photo 6x4 Vision Computer Centre, 24 Cross Street, Abergavenny Next door c2018

$2.38



Powered by WordPress. Designed by WooThemes