Associative semantic ranking of satellite images using PathFinder Network Scaling ensemble methods

This article proposes a methodology to reduce overfitting when ranking high-resolution satellite images by domain semantics. Our approach uses PathFinder Network Scaling ensemble methods. We generate cross-fold co-occurrence matrices for relevance of feature subspaces to each semantic. Each matrix is then reduced using the PathFinder network scaling algorithm. Irrelevant nodes are removed using node strength metrics resulting in an optimized model for ranking by semantic that generalizes better to new images. The experiments show that, when using this approach, the quality of ranking by semantic can be significantly improved. Results show that Mean Average Precision (MAP) of ranking over cross-fold experiments increased by a 13.2% while standard deviation of MAP was reduced by 16.8% relatively to experiments without PathFinder network scaling.