Domain-Adversarial Training of Self-Attention Based Networks for Land Cover Classification using Multi-temporal Sentinel-2 Satellite Imagery

04/01/2021
by   Martini Mauro, et al.
0

The increasing availability of large-scale remote sensing labeled data has prompted researchers to develop increasingly precise and accurate data-driven models for land cover and crop classification (LC CC). Moreover, with the introduction of self-attention and introspection mechanisms, deep learning approaches have shown promising results in processing long temporal sequences in the multi-spectral domain with a contained computational request. Nevertheless, most practical applications cannot rely on labeled data, and in the field, surveys are a time consuming solution that poses strict limitations to the number of collected samples. Moreover, atmospheric conditions and specific geographical region characteristics constitute a relevant domain gap that does not allow direct applicability of a trained model on the available dataset to the area of interest. In this paper, we investigate adversarial training of deep neural networks to bridge the domain discrepancy between distinct geographical zones. In particular, we perform a thorough analysis of domain adaptation applied to challenging multi-spectral, multi-temporal data, accurately highlighting the advantages of adapting state-of-the-art self-attention based models for LC CC to different target zones where labeled data are not available. Extensive experimentation demonstrated significant performance and generalization gain in applying domain-adversarial training to source and target regions with marked dissimilarities between the distribution of extracted features.

READ FULL TEXT

page 4

page 13

research
10/23/2019

Self-Attention for Raw Optical Satellite Time Series Classification

Deep learning methods have received increasing interest by the remote se...
research
08/28/2021

Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training for Road Segmentation of Remote Sensing Images

Road segmentation from remote sensing images is a challenging task with ...
research
02/26/2020

Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey

In many practical applications, it is often difficult and expensive to o...
research
06/16/2020

DSDANet: Deep Siamese Domain Adaptation Convolutional Neural Network for Cross-domain Change Detection

Change detection (CD) is one of the most vital applications in remote se...
research
07/11/2021

Leveraging Domain Adaptation for Low-Resource Geospatial Machine Learning

Machine learning in remote sensing has matured alongside a proliferation...
research
10/18/2021

Finding Strong Gravitational Lenses Through Self-Attention

The upcoming large scale surveys are expected to find approximately 10^5...
research
03/18/2021

Enhancing Transformer for Video Understanding Using Gated Multi-Level Attention and Temporal Adversarial Training

The introduction of Transformer model has led to tremendous advancements...

Please sign up or login with your details

Forgot password? Click here to reset