Do Deep Features Generalize from Everyday Objects to Remote Sensing and Aerial Scenes Domains?

Abstract

In this paper, we evaluate the generalization power of deep features (ConvNets) in two new scenarios: aerial and remote sensing image classification. We evaluate experimentally ConvNets trained for recognizing everyday objects for the classification of aerial and remote sensing images. ConvNets obtained the best results for aerial images, while for remote sensing, they performed well but were outperformed by low-level color descriptors, such as BIC. We also present a correlation analysis, showing the potential for combining/fusing different ConvNets with other descriptors or even for combining multiple ConvNets. A preliminary set of experiments fusing ConvNets obtains state-of-the-art results for the well-known UCMerced dataset.

Cite

Text

Penatti et al. "Do Deep Features Generalize from Everyday Objects to Remote Sensing and Aerial Scenes Domains?." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2015. doi:10.1109/CVPRW.2015.7301382

Markdown

[Penatti et al. "Do Deep Features Generalize from Everyday Objects to Remote Sensing and Aerial Scenes Domains?." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2015.](https://mlanthology.org/cvprw/2015/penatti2015cvprw-deep/) doi:10.1109/CVPRW.2015.7301382

BibTeX

@inproceedings{penatti2015cvprw-deep,
  title     = {{Do Deep Features Generalize from Everyday Objects to Remote Sensing and Aerial Scenes Domains?}},
  author    = {Penatti, Otávio Augusto Bizetto and Nogueira, Keiller and dos Santos, Jefersson Alex},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2015},
  pages     = {44-51},
  doi       = {10.1109/CVPRW.2015.7301382},
  url       = {https://mlanthology.org/cvprw/2015/penatti2015cvprw-deep/}
}