Global Land-Cover Mapping With Weak Supervision: Outcome of the 2020 IEEE GRSS Data Fusion Contest

Abstract

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 bestperforming methods during the contest. Index Terms-Image analysis and data fusion, multimodal, land cover mapping, weak supervision, deep learning, convolutional neural networks, random forests.

MARIDA: A benchmark for Marine Debris detection from Sentinel-2 remote sensing data

“…A RF classifier consists of many decision trees and uses averaging to improve the predictive performance and control over-fitting. For our RF model, we extracted features similar to the first place team of Track 2 of the 2020 IEEE GRSS Data Fusion Contest [58]. We trained three different RF models: i) one based on spectral signatures of each pixel (RF SS ), ii) one based on spectral signatures and calculated spectral indices (RF SS+SI ), and iii) one with spectral signatures, spectral indices, and extracted Gray-Level Co-occurrence Matrix (GLCM) [59] textural features (RF SS+SI+GLCM ) in order to incorporate the spatial information.…”

Top-Down Pyramid Fusion Network for High-Resolution Remote Sensing Semantic Segmentation

“…In addition, LiDAR data is also used in various remote sensing segmentation tasks [37][38][39]. Finally, the holding of various data fusion competitions [40][41][42] also greatly stimulated the enthusiasm of many researchers.…”

Report on the 2021 IEEE GRSS Data Fusion Contest—Geospatial Artificial Intelligence for Social Good [Technical Committees]

“…The ultimate goal of the contest is to build models to understand the state and changes in the manmade and natural environment using multisensor and multitemporal remote sensing data for sustainable development. This contest was designed as a benchmarking competition following previous editions [1], [2], [4], [6], [7]. The 2021 DFC had two tracks running in parallel: 1) Track DSE: detection of settlements without electricity 2) Track MSD: multitemporal semantic change detection.…”