Semi-Supervised Regression with Generative Adverserial Networks for End to End Learning in Autonomous Driving

This research concerns solving the semi-supervised learning problem with generative adversarial networks for regression. In contrast to classification, where only a limited number of distinct classes is given, the regression task is defined as predicting continuous labels for a given dataset. Semi-supervised learning is of vital importance for the applications where a small number of labeled samples is available, or labeling samples is difficult or expensive to collect. A case in point is autonomous driving in which obtaining sufficient labeled samples covering all driving conditions is costly. In this context, we can take advantage of semisupervised learning techniques with groundbreaking generative models, such as generative adversarial networks. However, almost all proposed GAN-based semisupervised techniques in the literature are focused on solving the classification problem. Hence, developing a GAN-based semi-supervised method for the regression task is still an open problem. To address this problem, we introduce Reg-GAN in two different architectures. In summary, our proposed method is able to predict continuous labels for a training dataset which has only a limited number of labeled samples. Moreover, the application of this technique for solving the end-to-end task in autonomous driving will be presented. We performed several experiments on a publicly available driving dataset to evaluate our proposed method, and the results are very promising. The results show that our approach generates images with high quality, gives smaller label prediction error and leads to a more stable training compared with the state-of-the-art Improved GAN technique (Salimans et al., 2016).