1 code implementation • 7 Aug 2023 • Artem Moskalev, Anna Sepliarskaia, Erik J. Bekkers, Arnold Smeulders
We demonstrate that even when a network learns to correctly classify samples on a group orbit, the underlying decision-making in such a model does not attain genuine invariance.
no code implementations • 19 Dec 2022 • Philipp Christian Petersen, Anna Sepliarskaia
We study the generalization capacity of group convolutional neural networks.
1 code implementation • 9 Oct 2022 • Artem Moskalev, Anna Sepliarskaia, Ivan Sosnovik, Arnold Smeulders
Symmetries built into a neural network have appeared to be very beneficial for a wide range of tasks as it saves the data to learn them.
no code implementations • 12 Oct 2019 • Anna Sepliarskaia, Julia Kiseleva, Maarten de Rijke
We conclude that existing metrics of disentanglement were created to reflect different characteristics of disentanglement and do not satisfy two basic desirable properties: (1) assign a high score to representations that are disentangled according to the definition; and (2) assign a low score to representations that are entangled according to the definition.