With the recent addition of large, curated and
labeled data sets to the remote sensing discipline, deep learning
models have largely surpassed the performance of classical
techniques. These deep models, typically Convolutional Neural
Networks, are invariant to translation through the use of successive
convolution layers which are themselves equivariant to
translation. Further, the combination of multiple convolution
and pooling layers means that in practice, the model is also
approximately invariant to translation. However, until recently
these models could only approach rotational invariance through
data augmentation. Here we propose using a new model formulation
which achieves rotational equaivariance without data
augmentation for overhead imagery classification. We utilize the
popular xView data set to compare the rotational equivariance
formalization against a regular CNN and CNN with rotational
data augmentation for the task of image classification.
Published: May 19, 2021
Citation
Bynum L., T.J. Doster, T.H. Emerson, and H.J. Kvinge. 2021.Rotational Equivariance for Object Classification Using xView. In IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2020), September 26 - October 2, 2020, Waikoloa, HI, 3684-3687. Piscataway, New Jersey:IEEE.PNNL-SA-150872.doi:10.1109/IGARSS39084.2020.9324015