Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation

by   Umberto Michieli, et al.

Deep learning techniques have been widely used in autonomous driving systems for the semantic understanding of urban scenes, however they need a huge amount of labeled data for training, which is difficult and expensive to acquire. A recently proposed workaround is to train deep networks using synthetic data, however the domain shift between real world and synthetic representations limits the performance. In this work a novel unsupervised domain adaptation strategy is introduced to solve this issue. The proposed learning strategy is driven by three components: a standard supervised learning loss on labeled synthetic data, an adversarial learning module that exploits both labeled synthetic data and unlabeled real data and finally a self-teaching strategy exploiting unlabeled data. The last component exploits a region growing framework guided by the segmentation confidence. Furthermore, we weighted this component on the basis of the class frequencies to enhance the performance on less common classes. Experimental results prove the effectiveness of the proposed strategy in adapting a segmentation network trained on synthetic datasets, like GTA5 and SYNTHIA, to real world datasets like Cityscapes and Mapillary.


page 1

page 3

page 7

page 10


Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training

Unsupervised Domain Adaptation (UDA) aims at improving the generalizatio...

Unsupervised Domain Adaptation for Mobile Semantic Segmentation based on Cycle Consistency and Feature Alignment

The supervised training of deep networks for semantic segmentation requi...

Unsupervised Domain Adaptation in Semantic Segmentation: a Review

The aim of this paper is to give an overview of the recent advancements ...

Domain Adaptation Using Adversarial Learning for Autonomous Navigation

Autonomous navigation has become an increasingly popular machine learnin...

Ensemble of Discriminators for Domain Adaptation in Multiple Sound Source 2D Localization

This paper introduces an ensemble of discriminators that improves the ac...

KLIEP-based Density Ratio Estimation for Semantically Consistent Synthetic to Real Images Adaptation in Urban Traffic Scenes

Synthetic data has been applied in many deep learning based computer vis...

Exploiting Image Translations via Ensemble Self-Supervised Learning for Unsupervised Domain Adaptation

We introduce an unsupervised domain adaption (UDA) strategy that combine...

Please sign up or login with your details

Forgot password? Click here to reset