Semi-Supervised Fine-Tuning for Deep Learning Models in Remote Sensing Applications
This work addresses remote sensing applications, but it is incremental as it applies existing SSL methods to a specific domain.
The paper tackled land cover identification by combining deep learning with semi-supervised learning (SSL) to enhance model performance, showing that SSL-enhanced loss functions improved results in pixel-level segmentation tasks over orthoimages.
A combinatory approach of two well-known fields: deep learning and semi supervised learning is presented, to tackle the land cover identification problem. The proposed methodology demonstrates the impact on the performance of deep learning models, when SSL approaches are used as performance functions during training. Obtained results, at pixel level segmentation tasks over orthoimages, suggest that SSL enhanced loss functions can be beneficial in models' performance.