Multi-Task Learning of Height and Semantics from Aerial Images

by   Marcela Carvalho, et al.

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


page 1

page 3

page 4

page 5


Multi-task learning of speech and speaker recognition

We study multi-task learning for two orthogonal speech technology tasks:...

Height Prediction and Refinement from Aerial Images with Semantic and Geometric Guidance

Deep learning provides a powerful new approach to many computer vision t...

A Generalized Multi-Task Learning Approach to Stereo DSM Filtering in Urban Areas

City models and height maps of urban areas serve as a valuable data sour...

Multi-Stage Prediction Networks for Data Harmonization

In this paper, we introduce multi-task learning (MTL) to data harmonizat...

Data Fusion for Multi-Task Learning of Building Extraction and Height Estimation

In accordance with the urban reconstruction problem proposed by the DFC2...

Multi-task Learning for Camera Calibration

For a number of tasks, such as 3D reconstruction, robotic interface, aut...

Facial Affect Analysis: Learning from Synthetic Data Multi-Task Learning Challenges

Facial affect analysis remains a challenging task with its setting trans...

Please sign up or login with your details

Forgot password? Click here to reset