Skip to Main content Skip to Navigation
Conference papers

SemI2I: Semantically Consistent Image-to-Image Translation for Domain Adaptation of Remote Sensing Data

Onur Tasar 1 S Happy 2 Yuliya Tarabalka 1 Pierre Alliez 1
1 TITANE - Geometric Modeling of 3D Environments
CRISAM - Inria Sophia Antipolis - Méditerranée
2 STARS - Spatio-Temporal Activity Recognition Systems
CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : Although convolutional neural networks have been proven to be an effective tool to generate high quality maps from remote sensing images, their performance significantly deteriorates when there exists a large domain shift between training and test data. To address this issue, we propose a new data augmentation approach that transfers the style of test data to training data using generative adversarial networks. Our semantic segmentation framework consists in first training a U-net from the real training data and then fine-tuning it on the test stylized fake training data generated by the proposed approach. Our experimental results prove that our framework outperforms the existing domain adaptation methods.
Complete list of metadata

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/hal-02487142
Contributor : Onur Tasar <>
Submitted on : Friday, February 21, 2020 - 1:52:32 PM
Last modification on : Thursday, January 21, 2021 - 2:32:02 PM
Long-term archiving on: : Friday, May 22, 2020 - 3:50:25 PM

File

SemI2I.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02487142, version 1

Citation

Onur Tasar, S Happy, Yuliya Tarabalka, Pierre Alliez. SemI2I: Semantically Consistent Image-to-Image Translation for Domain Adaptation of Remote Sensing Data. IGARSS 2020 - IEEE International Geoscience and Remote Sensing Symposium, Sep 2020, Waikoloa, Hawaii, United States. ⟨hal-02487142⟩

Share

Metrics

Record views

175

Files downloads

525