Domain Adversarial Neural Networks for Large-Scale Land Cover Classification

Abstract

Learning classification models require sufficiently labeled training samples, however, collecting labeled samples for every new problem is time-consuming and costly. An alternative approach is to transfer knowledge from one problem to another, which is called transfer learning. Domain adaptation (DA) is a type of transfer learning that aims to find a new latent space where the domain discrepancy between the source and the target domain is negligible. In this work, we propose an unsupervised DA technique called domain adversarial neural networks (DANNs), composed of a feature extractor, a class predictor, and domain classifier blocks, for large-scale land cover classification. Contrary to the traditional methods that perform representation and classifier learning in separate stages, DANNs combine them into a single stage, thereby learning a new representation of the input data that is both domain-invariant and discriminative. Once trained, the classifier of a DANN can be used to predict both source and target domain labels. Additionally, we also modify the domain classifier of a DANN to evaluate its suitability for multi-target domain adaptation problems. Experimental results obtained for both single and multiple target DA problems show that the proposed method provides a performance gain of up to 40%.

A Method for Vehicle Detection in High-Resolution Satellite Images that Uses a Region-Based Object Detector and Unsupervised Domain Adaptation

“…However, their experimental settings are not very challenging because the selected source and target domain area are very close, and there are only small feature differences between the two domains. Bejiga et al [38] adopted a promising adversarial training framework; however, their method could be improved by using GAN loss [35] instead of gradient reversal layer because [34] reported better results than [33]. Rostami et al [39] incorporated Sliced Wasserstein Distance (SWD) [40] with the classic distribution-matching method to deal with feature differences between electro-optical (EO) and synthetic aperture radar (SAR) images.…”

Different Spectral Domain Transformation for Land Cover Classification Using Convolutional Neural Networks with Multi-Temporal Satellite Imagery

“…CNNs are a type of deep learning method that use convolutional multiplication based on artificial neural networks [37]. Recently, CNN have been widely used in land cover classification, showing remarkable performance [18,19,32,33,[38][39][40][41]. Typical CNNs are composed of convolutional layers, pooling layers, and fully connected layers.…”

Assessing the Effect of Training Sampling Design on the Performance of Machine Learning Classifiers for Land Cover Mapping Using Multi-Temporal Remote Sensing Data and Google Earth Engine

“…But such methods require large, labeled datasets for training, which is not always feasible. However, recent studies such as Rostami et al [22] and Bejiga et al [23] provide an alternative approach to building training datasets using transfer learning methodologies that takes advantage of knowledge from existing data.…”