Deutsch
 
Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

 
 
DownloadE-Mail
  Multitask GANs for Semantic Segmentation and Depth Completion With Cycle Consistency

Zhang, C., Tang, Y., Zhao, C., Sun, Q., Ye, Z., Kurths, J. (2021): Multitask GANs for Semantic Segmentation and Depth Completion With Cycle Consistency. - IEEE Transactions on Neural Networks and Learning Systems, 32, 12, 5404-5415.
https://doi.org/10.1109/TNNLS.2021.3072883

Item is

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Zhang, Chongzhen1, Autor
Tang, Yang1, Autor
Zhao, Chaoqiang1, Autor
Sun, Qiyu 1, Autor
Ye, Zhencheng1, Autor
Kurths, Jürgen2, Autor              
Affiliations:
1External Organizations, ou_persistent22              
2Potsdam Institute for Climate Impact Research, ou_persistent13              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: Semantic segmentation and depth completion are two challenging tasks in scene understanding, and they are widely used in robotics and autonomous driving. Although several studies have been proposed to jointly train these two tasks using some small modifications, such as changing the last layer, the result of one task is not utilized to improve the performance of the other one despite that there are some similarities between these two tasks. In this article, we propose multitask generative adversarial networks (Multitask GANs), which are not only competent in semantic segmentation and depth completion but also improve the accuracy of depth completion through generated semantic images. In addition, we improve the details of generated semantic images based on CycleGAN by introducing multiscale spatial pooling blocks and the structural similarity reconstruction loss. Furthermore, considering the inner consistency between semantic and geometric structures, we develop a semantic-guided smoothness loss to improve depth completion results. Extensive experiments on the Cityscapes data set and the KITTI depth completion benchmark show that the Multitask GANs are capable of achieving competitive performance for both semantic segmentation and depth completion tasks.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2021-05-122021-12-30
 Publikationsstatus: Final veröffentlicht
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: Expertenbegutachtung
 Identifikatoren: DOI: 10.1109/TNNLS.2021.3072883
MDB-ID: No data to archive
PIKDOMAIN: RD4 - Complexity Science
Organisational keyword: RD4 - Complexity Science
Research topic keyword: Complex Networks
Research topic keyword: Complex Networks
Model / method: Machine Learning
Model / method: Nonlinear Data Analysis
 Art des Abschluß: -

Veranstaltung

einblenden:

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: IEEE Transactions on Neural Networks and Learning Systems
Genre der Quelle: Zeitschrift, SCI, Scopus
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: -
Seiten: - Band / Heft: 32 (12) Artikelnummer: - Start- / Endseite: 5404 - 5415 Identifikator: Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Anderer: 2162-237X
ISSN: 2162-237X
CoNE: https://publications.pik-potsdam.de/cone/journals/resource/IEEE-transactions-on-neural-networks-and-learning-systems