EUROPEAN MACHINE VISION FORUM
Turning Grand Theft Auto into a deep learning dataset
A group at the University of Bologna is making images from Grand Teſt Auto more realistic, so that they can act as training data for neural networks. Greg Blackman listened to Pierluigi Zama Ramirez’s presentation at the European Machine Vision Forum
W
hat can computer vision learn from video games? Researchers at the University of Bologna, in Italy, have
trained neural networks using images from the video game Grand Teſt Auto (GTA). Te idea is to see if the computer graphics from GTA can be made to seem like real images – from the neural network’s perspective at least. Pierluigi Zama Ramirez, a PhD student at
the University of Bologna, described the work at the European Machine Vision Association’s machine vision forum, held in Bologna, from 5 to 7 September. One of the big problems with deep learning,
Zama Ramirez explained, is annotating the large amount of image data needed to get an accurate output from a neural network. He said that a task like semantic segmentation – classifying
12 Imaging and Machine Vision Europe • October/November 2018
each pixel of the image – mostly has to be done manually, which can take two to six hours for each image. Te advantage of training a neural network
on synthetic data, such as those produced by computer graphics, is that ‘you can obtain the labels almost for free’, Zama Ramirez said, as well as having access to a lot of images. Te downside is that the models trained
on synthetic data cannot achieve the same performance as models trained on real data. Te researchers therefore set about trying
to make GTA images look more realistic using generative adversarial networks (GANs). Tis is a framework that consists of two neural networks: a generator and a discriminator. Te generator takes a synthetic image from the video game and tries to transform it into a realistic
@imveurope
www.imveurope.com
Andrey Slepov/
Shutterstock.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72
