Caleb Robinson, Kolya Malkin, Nebojsa Jojic, Huijun Chen, Rongjun Qin, Changlin Xiao, Michael Schmitt, Pedram Ghamisi, Ronny Hansch, and Naoto Yokoya

regions of interest

Regions of interest of the DFC2020 dataset: (A) Khabarovsk, Russia, (B) Mumbai, India, (C) Kippa Ring, Australia, (D) Mexico City, Mexico, (E) Bandar Anzali, Iran, (F) Black Forest, Germany, (G) Cape Town, South Africa.

This paper presents the scientific outcomes of the 2020 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The 2020 Contest addressed the problem of automatic global land-cover mapping with weak supervision, i.e. estimating high-resolution semantic maps while only low-resolution reference data is available during training. Two separate competitions were organized to assess two different scenarios: 1) high-resolution labels are not available at all and 2) a small amount of high-resolution labels are available additionally to low-resolution reference data. In this paper we describe the DFC2020 dataset that remains available for further evaluation of corresponding approaches and report the results of the best-performing methods during the contest.

 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021-03-04.

View paper
IARAI Authors
Dr. Pedram Ghamisi
Weather and Physics
Convolutional Neural Networks, Data Fusion, Deep Learning, Remote Sensing, Weak Supervision


Imprint | Privacy Policy

Stay in the know with developments at IARAI

We can let you know if there’s any

updates from the Institute.
You can later also tailor your news feed to specific research areas or keywords (Privacy)

Log in with your credentials

Forgot your details?

Create Account