DAugNet: Unsupervised, Multi-source, Multi-target, and Life-long Domain Adaptation for Semantic Segmentation of Satellite Images
- Others:
- Geometric Modeling of 3D Environments (TITANE) ; Inria Sophia Antipolis - Méditerranée (CRISAM) ; Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
- Centre National d'Études Spatiales [Toulouse] (CNES)
- Analytic and Computational Research, Inc. - Earth Sciences (ACRI-ST)
- CNES, ACRI-ST and ANR-19-P3IA-0002 - 3IA Côte d'Azur - Nice - Interdisciplinary Institute for Artificial Intelligence
- ANR-19-P3IA-0002,3IA@cote d'azur,3IA Côte d'Azur(2019)
Description
The domain adaptation of satellite images has recently gained an increasing attention to overcome the limited generalization abilities of machine learning models when segmenting large-scale satellite images. Most of the existing approaches seek for adapting the model from one domain to another. However, such single-source and single-target setting prevents the methods from being scalable solutions, since nowadays multiple source and target domains having different data distributions are usually available. Besides, the continuous proliferation of satellite images necessitates the classifiers to adapt to continuously increasing data. We propose a novel approach, coined DAugNet, for unsupervised, multi-source, multi-target, and life-long domain adaptation of satellite images. It consists of a classifier and a data augmentor. The data augmentor, which is a shallow network, is able to perform style transfer between multiple satellite images in an unsupervised manner, even when new data are added over the time. In each training iteration, it provides the classifier with diversified data, which makes the classifier robust to large data distribution difference between the domains. Our extensive experiments prove that DAugNet significantly better generalizes to new geographic locations than the existing approaches.
Abstract
International audience
Additional details
- URL
- https://hal.archives-ouvertes.fr/hal-02893533
- URN
- urn:oai:HAL:hal-02893533v1
- Origin repository
- UNICA