Affine Equivariant Networks Based on Differential Invariants
Convolutional neural networks benefit from translation equivariance achieving tremendous
success. Equivariant networks further extend this property to other transformation groups …
success. Equivariant networks further extend this property to other transformation groups …
Moving frame net: SE (3)-equivariant network for volumes
M Sangalli, S Blusseau… - … on Symmetry and …, 2023 - proceedings.mlr.press
Equivariance of neural networks to transformations helps to improve their performance and
reduce generalization error in computer vision tasks, as they apply to datasets presenting …
reduce generalization error in computer vision tasks, as they apply to datasets presenting …
Scale generalisation properties of extended scale-covariant and scale-invariant Gaussian derivative networks on image datasets with spatial scaling variations
A Perzanowski, T Lindeberg - arXiv preprint arXiv:2409.11140, 2024 - arxiv.org
This paper presents an in-depth analysis of the scale generalisation properties of the scale-
covariant and scale-invariant Gaussian derivative networks, complemented with both …
covariant and scale-invariant Gaussian derivative networks, complemented with both …
Equivariant Deep Learning Based on Scale-Spaces and Moving Frames
M Sangalli - 2022 - pastel.hal.science
In the context of neural networks, equivariance or invariance to transformations can induce a
better generalization to new data as soon as the data is symmetric to the relevant …
better generalization to new data as soon as the data is symmetric to the relevant …
[引用][C] Equivariant Deep Learning Based on Scale-Spaces and Moving Frames.(Apprentissage Profond Équivariant Basé sur les Espaces d'Échelle et les Repères …
M Sangalli - 2022 - PSL University, Paris, France