Adversarial Learning for Knowledge Adaptation From Multiple Remote Sensing Sources

In this work, we introduce a neural architecture to unsupervised domain from multiple source domains. This architecture uses an EfficientNet as a feature extractor coupled with a set of Softmax classifiers equal to the number of source domains followed by an opportune fusion layer. To reduce the domain discrepancy between each source and target domain, we adopt a Minmax entropy approach that is based on the idea of optimizing in an adversarial manner the conditional entropy of the target samples with respect to each source classifier and minimizes it with respect to the feature extractor. As for the fusion module, we propose a weighted average fusion layer with learnable weights for aggregating the outputs of the different Softmax classifiers. Experiments on a multisource data set composed of images acquired by manned and unmanned aerial vehicles (MAVs/UAVs) over different locations are reported and discussed.

Automated summary

In this work, a neural architecture is introduced for unsupervised domain adaptation from multiple source domains, employing a Minmax entropy approach to reduce domain discrepancy. Experimental results demonstrate the effectiveness of the proposed method.