A multi-task deep learning framework coupling semantic segmentation and image reconstruction for very high resolution imagery

Maria Papadomanolaki; Konstantinos Karantzalos; Maria Vakalopoulou

A multi-task deep learning framework coupling semantic segmentation and image reconstruction for very high resolution imagery

Maria Papadomanolaki ^{1, 2, 3} Konstantinos Karantzalos ⁴ Maria Vakalopoulou ^{5, 3}

1 CentraleSupélec

2 NTUA - National Technical University of Athens [Athens]

3 OPIS - OPtimisation Imagerie et Santé

Inria Saclay - Ile de France, CVN - Centre de vision numérique

4 Remote Sensing Laboratory

5 ENPC - École des Ponts ParisTech

Keywords : Fully-convolutional networks Autoencoders Limited annotations Feature representations Deep learning

Document type :

Conference papers

Domain :

Computer Science [cs] / Computer Vision and Pattern Recognition [cs.CV]

Complete list of metadatas

Cited literature [11 references] Display Hide Download

https://hal.inria.fr/hal-02266085
Contributor : Maria Papadomanolaki <>
Submitted on : Tuesday, August 13, 2019 - 12:24:05 PM
Last modification on : Tuesday, January 14, 2020 - 1:08:02 PM
Long-term archiving on: Thursday, January 9, 2020 - 10:18:31 PM

20190527122343_978326_4652.pdf

Files produced by the author(s)

A multi-task deep learning framework coupling semantic segmentation and image reconstruction for very high resolution imagery

File

Identifiers

Collections

Citation

Export

Metrics

70

846

Contact

A multi-task deep learning framework coupling semantic segmentation and image reconstruction for very high resolution imagery

File

Identifiers

Collections

Citation

Export

Share

Metrics

70

846

Contact