Unsupervised Domain Adaptation using Generative Adversarial Networks for Semantic Segmentation of Aerial Images
This addresses the challenge of adapting segmentation models for surveillance and urban scene understanding across different cities, though it is incremental as it builds on existing GAN-based domain adaptation techniques.
The paper tackles the problem of domain shift in semantic segmentation of aerial images when deploying a pre-trained model to a new city, using Generative Adversarial Networks (GANs) to reduce this impact. The method improves overall accuracy from 35% to 52% and increases average segmentation accuracy for inverted classes from 14% to 61% on the ISPRS dataset.
Segmenting aerial images is being of great potential in surveillance and scene understanding of urban areas. It provides a mean for automatic reporting of the different events that happen in inhabited areas. This remarkably promotes public safety and traffic management applications. After the wide adoption of convolutional neural networks methods, the accuracy of semantic segmentation algorithms could easily surpass 80% if a robust dataset is provided. Despite this success, the deployment of a pre-trained segmentation model to survey a new city that is not included in the training set significantly decreases the accuracy. This is due to the domain shift between the source dataset on which the model is trained and the new target domain of the new city images. In this paper, we address this issue and consider the challenge of domain adaptation in semantic segmentation of aerial images. We design an algorithm that reduces the domain shift impact using Generative Adversarial Networks (GANs). In the experiments, we test the proposed methodology on the International Society for Photogrammetry and Remote Sensing (ISPRS) semantic segmentation dataset and found that our method improves the overall accuracy from 35% to 52% when passing from Potsdam domain (considered as source domain) to Vaihingen domain (considered as target domain). In addition, the method allows recovering efficiently the inverted classes due to sensor variation. In particular, it improves the average segmentation accuracy of the inverted classes due to sensor variation from 14% to 61%.