Multitask Learning of Height and Semantics From Aerial Images

被引：35

作者：

Carvalho, Marcela ^{[1
]}

Le Saux, Bertrand ^{[1
]}

Trouve-Peloux, Pauline ^{[1
]}

Champagnat, Frederic ^{[1
]}

Almansa, Andres ^{[2
]}

机构：

[1] Univ Paris Saclay, ONERA, DTIS, F-91123 Palaiseau, France

[2] Univ Paris 05, MAP5, F-75006 Paris, France

来源：

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2020年 / 17卷 / 08期

关键词：

Semantics; Task analysis; Training; Estimation; Predictive models; Decoding; Land surface; Aerial imagery; deep learning; multitask learning; neural networks; semantic segmentation; single view depth estimation; DEEP; CLASSIFICATION;

D O I：

10.1109/LGRS.2019.2947783

中图分类号：

P3 [地球物理学]; P59 [地球化学];

学科分类号：

0708 ; 070902 ;

摘要：

Aerial or satellite imagery is a great source for land surface analysis, which might yield land-use maps or elevation models. In this letter, we present a neural network framework for learning semantics and local height together. We show how this joint multitask learning benefits to each task on the large data set of the 2018 Data Fusion Contest. Moreover, our framework also yields an uncertainty map that allows assessing the prediction of the model. Code is available at https://github.com/marcelampc/mtl_aerial_images

引用

页码：1391 / 1395

页数：5

共 50 条

[31] 4T-Net: Multitask deep learning for nuclear analysis from pathology images
Vo, Vi Thi-Tuong
Noh, Myung-Giun
Kim, Soo-Hyung
[J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (29) : 73031 - 73053
[32] Learning and Sharing: A Multitask Genetic Programming Approach to Image Feature Learning
Bi, Ying
Xue, Bing
Zhang, Mengjie
[J]. IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2022, 26 (02) : 218 - 232
[33] A Novel Contrastive Learning Model for Aerial Images
Zhen, Taihang
Chen, Kai
Gao, Yang
[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2024, 21
[34] Ship velocity estimation in SAR images using multitask deep learning
Heiselberg, Peder
Sorensen, Kristian
Heiselberg, Henning
[J]. REMOTE SENSING OF ENVIRONMENT, 2023, 288
[35] Vehicle Detection from Aerial Images Using Deep Learning: A Comparative Study
Ammar, Adel
Koubaa, Anis
Ahmed, Mohanned
Saad, Abdulrahman
Benjdira, Bilel
[J]. ELECTRONICS, 2021, 10 (07)
[36] Multitask Deep Learning With Spectral Knowledge for Hyperspectral Image Classification
Liu, Shengjie
Shi, Qian
[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2020, 17 (12) : 2110 - 2114
[37] Efficient Multitask Multiple Kernel Learning With Application to Cancer Research
Rahimi, Arezou
Gonen, Mehmet
[J]. IEEE TRANSACTIONS ON CYBERNETICS, 2022, 52 (09) : 8716 - 8728
[38] Mood Prediction Based on Calendar Events Using Multitask Learning
Tateyama, Naoki
Fukui, Rui
Warisawa, Shin'ichi
[J]. IEEE ACCESS, 2022, 10 : 79747 - 79759
[39] Leveraging large-scale aerial data for accurate urban rooftop solar potential estimation via multitask learning
Boccalatte, Alessia
Jha, Ankit
Chanussot, Jocelyn
[J]. SOLAR ENERGY, 2025, 290
[40] Compositional Semantics Network With Multi-Task Learning for Pun Location
Mao, Junyu
Wang, Rongbo
Huang, Xiaoxi
Chen, Zhiqun
[J]. IEEE ACCESS, 2020, 8 : 44976 - 44982

← 1 2 3 4 5 →