Fast, Accurate Detection of 100,000 Object Classes on a Single Machine a prizewinning paper by Google Research scientists, describes a breakthrough in machine vision that can distinguish between a huge class of objects 20,000 times faster than before.
This so-called convolution operator is one of the key operations used in computer vision and, more broadly, all of signal processing. Unfortunately, it is computationally expensive and hence researchers use it sparingly or employ exotic SIMD hardware like GPUs and FPGAs to mitigate the computational cost. We turn things on their head by showing how one can use fast table lookup — a method called hashing — to trade time for space, replacing the computationally-expensive inner loop of the convolution operator — a sequence of multiplications and additions — required for performing millions of convolutions with a single table lookup.
We demonstrate the advantages of our approach by scaling object detection from the current state of the art involving several hundred or at most a few thousand of object categories to 100,000 categories requiring what would amount to more than a million convolutions. Moreover, our demonstration was carried out on a single commodity computer requiring only a few seconds for each image. The basic technology is used in several pieces of Google infrastructure and can be applied to problems outside of computer vision such as auditory signal processing.
Fast, Accurate Detection of 100,000 Object Classes on a Single Machine
(Image: Clutter, a Creative Commons Attribution Share-Alike (2.0) image from neofob's photostream)
KSU plant biochemical geneticist Raj Nagarajan describes the properties of Thaumatin, Monellin and Brazzein, all found in west African plants that are generally considered safe for consumption; each is a protein, and they are, respectively, 1,000x, 2000x, and 3000x sweeter than sugar.
In a new paper published in the peer-reviewed Journal of Ethnicity in Criminal Justice, sociologists and criminologists from University at Buffalo (SUNY), the University of Alabama, Kennesaw State University, the State of Georgia, and Georgia State University review 40 years’ worth of FBI data on violent crimes and property crimes, correlating this data series with […]
Address space layout randomization is an important first line of defense against malicious software: by randomizing where in memory instructions are stored, ASLR makes it much harder to overwrite memory with new code that will be jumped to as a program executes, offering significant protection against buffer overflow attacks.
Having a luxurious bed isn’t just a fairy tale from a catalog; it is a real, affordable possibility with offerings like this Olive+Owen bedroom set. If you’re thinking of doing some “spring cleaning”, this bed set is an easy way to completely upgrade your room in one purchase.This 20-piece collection has all of the expected slumberland elements, […]
Python is immensely popular in the data science world for the same reason it is in most other areas of computing—it has highly readable syntax and is suitable for anything from short scripts to massive web services. One of its most exciting, newest applications, however, is in machine learning. You can dive into this booming […]
Learning new skills is a great way to improve your resume and stand out from other candidates. Especially in a workforce in which many job-seekers have a wide variety of qualifications. With lifetime access to Virtual Training Company, you won’t have to choose a specific focus. You can pick up new expertise whenever you deem it […]