TY - JOUR
T1 - Semisupervised and weakly supervised road detection based on generative adversarial networks
AU - Han, Xiaofeng
AU - Lu, Jianfeng
AU - Zhao, Chunxia
AU - You, Shaodi
AU - Li, Hongdong
N1 - Publisher Copyright:
© 1994-2012 IEEE.
PY - 2018/4
Y1 - 2018/4
N2 - Road detection is a key component of autonomous driving; however, most fully supervised learning road detection methods suffer from either insufficient training data or high costs of manual annotation. To overcome these problems, we propose a semisupervised learning (SSL) road detection method based on generative adversarial networks (GANs) and a weakly supervised learning (WSL) method based on conditional GANs. Specifically, in our SSL method, the generator generates the road detection results of labeled and unlabeled images, and then they are fed into the discriminator, which assigns a label on each input to judge whether it is labeled. Additionally, in WSL method we add another network to predict road shapes of input images and use them in both generator and discriminator to constrain the learning progress. By training under these frameworks, the discriminators can guide a latent annotation process on the unlabeled data; therefore, the networks can learn better representations of road areas and leverage the feature distributions on both labeled and unlabeled data. The experiments are carried out on KITTI ROAD benchmark, and the results show our methods achieve the state-of-the-art performances.
AB - Road detection is a key component of autonomous driving; however, most fully supervised learning road detection methods suffer from either insufficient training data or high costs of manual annotation. To overcome these problems, we propose a semisupervised learning (SSL) road detection method based on generative adversarial networks (GANs) and a weakly supervised learning (WSL) method based on conditional GANs. Specifically, in our SSL method, the generator generates the road detection results of labeled and unlabeled images, and then they are fed into the discriminator, which assigns a label on each input to judge whether it is labeled. Additionally, in WSL method we add another network to predict road shapes of input images and use them in both generator and discriminator to constrain the learning progress. By training under these frameworks, the discriminators can guide a latent annotation process on the unlabeled data; therefore, the networks can learn better representations of road areas and leverage the feature distributions on both labeled and unlabeled data. The experiments are carried out on KITTI ROAD benchmark, and the results show our methods achieve the state-of-the-art performances.
KW - Generative adversarial networks
KW - road detection
KW - semi-supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85042699361&partnerID=8YFLogxK
U2 - 10.1109/LSP.2018.2809685
DO - 10.1109/LSP.2018.2809685
M3 - Article
SN - 1070-9908
VL - 25
SP - 551
EP - 555
JO - IEEE Signal Processing Letters
JF - IEEE Signal Processing Letters
IS - 4
ER -