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.
@article{arxiv.1707.05683,
title = {Exploiting Convolutional Representations for Multiscale Human Settlement Detection},
author = {Dalton Lunga and Dilip Patlolla and Lexie Yang and Jeanette Weaver and Budhendra Bhadhuri},
journal= {arXiv preprint arXiv:1707.05683},
year = {2017}
}