Sketch-a-Net that Beats Humans

Published in British Machine Vision Conference (BMVC), Best Paper, 2015

Qian Yu*, Yongxin Yang*, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales

We propose a multi-scale multi-channel deep neural network framework that, for the first time, yields sketch recognition performance surpassing that of humans. Our superior performance is a result of explicitly embedding the unique characteristics of sketches in our model.

This paper won the Best Science Paper at the British Machine Vision Conference 2015. The conferencde version is here and its extension was published in IJCV.