Warped convolutions: Efficient invariance to spatial transformations
Convolutional Neural Networks (CNNs) are extremely efficient, since they exploit the inherent translation-invariance of natural images. However, translation is just one of a myriad of useful spatial transformations. Can the same efficiency be attained when considering other spatial invariances? Such...
Main Authors: | Henriques, J, Vedaldi, A |
---|---|
Format: | Conference item |
Language: | English |
Published: |
Proceedings of Machine Learning Research
2017
|
Similar Items
-
Curvature Invariants for the Alcubierre and Natário Warp Drives
by: Brandon Mattingly, et al.
Published: (2021-01-01) -
Curvature Invariants for the Accelerating Natário Warp Drive
by: Brandon Mattingly, et al.
Published: (2020-09-01) -
Conv2Warp: An unsupervised deformable image registration with continuous convolution and warping
by: Ali, S, et al.
Published: (2019) -
A multiple waveguide invariant estimation method based on the warping transform and variational mode decomposition
by: Shoudong Wang, et al.
Published: (2024-02-01) -
Invariant information clustering for unsupervised image classification and segmentation
by: Ji, X, et al.
Published: (2020)