Exploiting Convolutional Representations for Multiscale Human Settlement Detection
This work addresses remote sensing applications by offering a potentially efficient method for feature reuse, though it appears incremental as it builds on existing convolutional networks.
The paper tackles the problem of multiscale human settlement detection in remote sensing by proposing a unified feature extraction framework that reuses trained convolutional feature extractors without retraining, achieving preliminary inductive transfer learning across superpixel mapping, pixel-level segmentation, and semantic image visualization tasks.
We test this premise and explore representation spaces from a single deep convolutional network and their visualization to argue for a novel unified feature extraction framework. The objective is to utilize and re-purpose trained feature extractors without the need for network retraining on three remote sensing tasks i.e. superpixel mapping, pixel-level segmentation and semantic based image visualization. By leveraging the same convolutional feature extractors and viewing them as visual information extractors that encode different image representation spaces, we demonstrate a preliminary inductive transfer learning potential on multiscale experiments that incorporate edge-level details up to semantic-level information.