The brain performs very complex computational tasks when identifying what is being seen by the eyes and modern computer vision systems come nowhere near that ability. Scientists from Harvard and MIT are working on adapting computer graphics processors to this specific task in an attempt to reverse engineer some of the characteristics of biologic visual systems.
To tackle this problem, the team drew inspiration from screening techniques in molecular biology, where a multitude of candidate organisms or compounds are screened in parallel to find those that have a particular property of interest. Rather than building a single model and seeing how well it could recognize visual objects, the team constructed thousands of candidate models, and screened for those that performed best on an object recognition task.
The resulting models outperformed a crop of state-of-the-art computer vision systems across a range of test sets, more accurately identifying a range of objects on random natural backgrounds with variation in position, scale, and rotation.
Using ordinary computer processing units, the effort would have required either years of time or millions of dollars of computing hardware. Instead, by harnessing modern graphics hardware, the analysis was done in just one week, and at a small fraction of the cost.
“GPUs are a real game-changer for scientific computing. We made a powerful parallel computing system from cheap, readily available off-the-shelf components, delivering over hundred-fold speed-ups relative to conventional methods,” says Pinto [Nicolas Pinto, Ph.D. candidate at MIT]. “With this expanded computational power, we can discover new vision models that traditional methods miss.”
Press release: Researchers demonstrate a better way for computers to ‘see’…
Article in PLoS Computational Biology: A High-Throughput Screening Approach to Discovering Good Forms of Biologically Inspired Visual Representation
(hat tip: Engadget)