Code and pretrained convnet models for classification of high resolution remote sensing (HRRS) images. The convnets are trained/fine-tuned on publicly available AID dataset of HRRS images (http://captain.whu.edu.cn/project/AID/). The collection contains the following datasets: Trained convnet models - models trained from scratch on AID dataset Fine-tuned convnet models - models pretrained on ImageNet and fine-tuned on AID dataset Tools & Results - code of an experimental framework for training and testing different convnet topologies for HRRS image classification, conference paper and presentation.
on Aug 17, 2018
R. Pilipović and V. Risojević, “Evaluation of Convnets for Large-Scale Scene Classification From High-Resolution Remote Sensing Images”, In Proc. 17th International Conference on Smart Technologies, IEEE EUROCON 2017, pp. 932-937. IEEE, 2017