Generalized knowledge distillation for multi-sensor remote sensing classification: an application to land cover mapping
Due to the proliferation of Earth Observation programmes, information at different spatial, spectral and temporal resolution is collected by means of various sensors (optical, radar, hyperspectral, LiDAR, etc.). Despite such abundance of information, it is not always possible to obtain a complete coverage of the same area (especially for large ones) from all the different sensors due to: (i) atmospheric conditions and/or (ii) acquisition cost. In this context of data (or modalities) misalignment, only part of the area under consideration could be covered by the different sensors (modalities). Unfortunately, standard machine learning approaches commonly employed in operational Earth monitoring systems require consistency between training and test data (i.e., they need to match the same information schema). Such a constraint limits the use of additional fruitful information, i.e., information coming from a particular sensor that may be available at training but not at test time. Recently, a framework able to manage such information misalignment between training and test information is proposed under the name of Generalized Knowledge Distillation (GKD). With the aim to provide a proof of concept of GKD in the context of multi-source Earth Observation analysis, here we provide a Generalized Knowledge Distillation framework for land use land cover mapping involving radar (Sentinel-1) and optical (Sentinel-2) satellite image time series data (SITS). Considering that part of the optical information may not be available due to bad atmospheric conditions, we make the assumption that radar SITS are always available (at both training and test time) while optical SITS are only accessible when the model is learnt (i.e., it is considered as privileged information). Evaluations are carried out on a real-world study area in the southwest of France, namely Dordogne, considering a mapping task involving seven different land use land cover classes. Experimental results underline how the additional (privileged) information ameliorates the results of the radar based classification with a main gain on the agricultural classes.
Main Author: | |
---|---|
Format: | conference_item biblioteca |
Language: | eng |
Published: |
ISPRS
|
Online Access: | http://agritrop.cirad.fr/597792/ http://agritrop.cirad.fr/597792/1/isprs-annals-V-2-2020-997-2020.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Summary: | Due to the proliferation of Earth Observation programmes, information at different spatial, spectral and temporal resolution is collected by means of various sensors (optical, radar, hyperspectral, LiDAR, etc.). Despite such abundance of information, it is not always possible to obtain a complete coverage of the same area (especially for large ones) from all the different sensors due to: (i) atmospheric conditions and/or (ii) acquisition cost. In this context of data (or modalities) misalignment, only part of the area under consideration could be covered by the different sensors (modalities). Unfortunately, standard machine learning approaches commonly employed in operational Earth monitoring systems require consistency between training and test data (i.e., they need to match the same information schema). Such a constraint limits the use of additional fruitful information, i.e., information coming from a particular sensor that may be available at training but not at test time. Recently, a framework able to manage such information misalignment between training and test information is proposed under the name of Generalized Knowledge Distillation (GKD). With the aim to provide a proof of concept of GKD in the context of multi-source Earth Observation analysis, here we provide a Generalized Knowledge Distillation framework for land use land cover mapping involving radar (Sentinel-1) and optical (Sentinel-2) satellite image time series data (SITS). Considering that part of the optical information may not be available due to bad atmospheric conditions, we make the assumption that radar SITS are always available (at both training and test time) while optical SITS are only accessible when the model is learnt (i.e., it is considered as privileged information). Evaluations are carried out on a real-world study area in the southwest of France, namely Dordogne, considering a mapping task involving seven different land use land cover classes. Experimental results underline how the additional (privileged) information ameliorates the results of the radar based classification with a main gain on the agricultural classes. |
---|