Communications of the ACM
Researchers Demonstrate a Better Way for Computers to 'See'
MIT and Harvard researchers used 16 GPUs to built this 18-inch cubed supercomputer as part of their research to build artificial vision systems inspired by the human brain.
Credit: Nicolas Pinto / MIT
Taking inspiration from genetic screening techniques, researchers from MIT and Harvard have demonstrated a way to build better artificial visual systems with the help of low-cost, high-performance gaming hardware.
The neural processing involved in visually recognizing even the simplest object in a natural environment is profound — and profoundly difficult to mimic. Neuroscientists have made broad advances in understanding the human visual system, but much of the inner workings of biologically-based systems remain a mystery. Using graphics processing units (GPUs) — the same technology video game designers use to render life-like graphics — MIT and Harvard researchers are now making progress faster than ever before.
"We made a powerful computing system that delivers over hundred fold speed-ups relative to conventional methods," says Nicolas Pinto, a PhD candidate in James DiCarlo's lab at the McGovern Institute for Brain Research at MIT. "With this extra computational power, we can discover new vision models that traditional methods miss." Pinto co-authored the study with David Cox of the Visual Neuroscience Group at the Rowland Institute at Harvard, published in PLoS Computational Biology as "A High-Throughput Screening Approach to Discovering Good Forms of Biologically Inspired Visual Representation."
Harnessing the processing power of dozens of high-performance Nvidia graphics cards and PlayStation 3 gaming devices, the team designed a high-throughput screening process to tease out the best parameters for visual object recognition tasks. The resulting model outperformed a crop of state-of-the-art vision systems across a range of tests — more accurately identifying a range of objects on random natural backgrounds with variation in position, scale, and rotation. Had the team used conventional computational tools, the one-week screening phase would have taken over two years to complete.
The researchers say that their high-throughput approach could be applied to other areas of computer vision, such as face identification, object tracking, pedestrian detection for automotive applications, and gesture and action recognition. Moreover, as scientists better understand what components make a good artificial vision system, they can use these hints to better understand the human brain as well.
View a video of MIT and Harvard researchers' approach to helping computers to 'see.'
No entries found