No More Discrimination: Cross City Adaptation of Road Scene Segmenters

TL;DR

This paper introduces an unsupervised domain adaptation method for road scene segmentation that leverages Google Street View's time-machine feature and domain adversarial learning to adapt models across cities without annotations.

Contribution

It presents a novel unsupervised adaptation framework using static-object priors and domain adversarial learning, eliminating the need for annotated data in new cities.

Findings

Improves segmentation accuracy across multiple cities.

Outperforms state-of-the-art methods requiring annotations.

Effective without any user-provided annotations.

Abstract

Despite the recent success of deep-learning based semantic segmentation, deploying a pre-trained road scene segmenter to a city whose images are not presented in the training set would not achieve satisfactory performance due to dataset biases. Instead of collecting a large number of annotated images of each city of interest to train or refine the segmenter, we propose an unsupervised learning approach to adapt road scene segmenters across different cities. By utilizing Google Street View and its time-machine feature, we can collect unannotated images for each road scene at different times, so that the associated static-object priors can be extracted accordingly. By advancing a joint global and class-specific domain adversarial learning framework, adaptation of pre-trained segmenters to that city can be achieved without the need of any user annotation or interaction. We show that our method improves the performance of semantic segmentation in multiple cities across continents, while it performs favorably against state-of-the-art approaches requiring annotated training data.