Understanding when spatial transformer networks do not support invariance, and what to do about it

Lukas Finnveden, Ylva Jansson, Tony Lindeberg. Understanding when spatial transformer networks do not support invariance, and what to do about it. In 25th International Conference on Pattern Recognition, ICPR 2020, Virtual Event / Milan, Italy, January 10-15, 2021. pages 3427-3434, IEEE, 2020. [doi]

@inproceedings{FinnvedenJL20,
  title = {Understanding when spatial transformer networks do not support invariance, and what to do about it},
  author = {Lukas Finnveden and Ylva Jansson and Tony Lindeberg},
  year = {2020},
  doi = {10.1109/ICPR48806.2021.9412997},
  url = {https://doi.org/10.1109/ICPR48806.2021.9412997},
  researchr = {https://researchr.org/publication/FinnvedenJL20},
  cites = {0},
  citedby = {0},
  pages = {3427-3434},
  booktitle = {25th International Conference on Pattern Recognition, ICPR 2020, Virtual Event / Milan, Italy, January 10-15, 2021},
  publisher = {IEEE},
  isbn = {978-1-7281-8808-9},
}