2018 Low-Power Image Recognition Challenge
It addresses the need for low-power computer vision in battery-powered systems like drones and mobile phones, but is incremental as it reports on an ongoing competition.
The paper summarizes the 2018 Low-Power Image Recognition Challenge, which aimed to improve technologies for efficient and accurate object classification and detection in images, with winners' scores improving over 24 times across four years.
The Low-Power Image Recognition Challenge (LPIRC, https://rebootingcomputing.ieee.org/lpirc) is an annual competition started in 2015. The competition identifies the best technologies that can classify and detect objects in images efficiently (short execution time and low energy consumption) and accurately (high precision). Over the four years, the winners' scores have improved more than 24 times. As computer vision is widely used in many battery-powered systems (such as drones and mobile phones), the need for low-power computer vision will become increasingly important. This paper summarizes LPIRC 2018 by describing the three different tracks and the winners' solutions.