1 code implementation • 12 Jan 2023 • Luis Armando Pérez Rey, Giovanni Luca Marchetti, Danica Kragic, Dmitri Jarnikov, Mike Holenderski
We introduce Equivariant Isomorphic Networks (EquIN) -- a method for learning representations that are equivariant with respect to general group actions over data.
no code implementations • 1 Jan 2021 • Luis Armando Pérez Rey, Berk İşler, Mike Holenderski, Dmitri Jarnikov
In image-based object classification, the visual appearance of objects determines which class they are assigned to.
no code implementations • 26 Nov 2020 • Luis A. Pérez Rey, Loek Tonnaer, Vlado Menkovski, Mike Holenderski, Jacobus W. Portegies
We propose a metric for the evaluation of the level of LSBD that a data representation achieves.
1 code implementation • NeurIPS 2021 • Loek Tonnaer, Luis A. Pérez Rey, Vlado Menkovski, Mike Holenderski, Jacobus W. Portegies
The definition of Linear Symmetry-Based Disentanglement (LSBD) formalizes the notion of linearly disentangled representations, but there is currently no metric to quantify LSBD.
no code implementations • 28 Sep 2020 • Loek Tonnaer, Luis Armando Pérez Rey, Vlado Menkovski, Mike Holenderski, Jacobus W. Portegies
Although several works focus on learning LSBD representations, such methods require supervision on the underlying transformations for the entire dataset, and cannot deal with unlabeled data.
no code implementations • 22 Sep 2020 • Marijn van Knippenberg, Mike Holenderski, Vlado Menkovski
Deep Learning may provide solutions which are less time-consuming and of higher quality at large scales, as it generally does not need to generate solutions in an iterative manner, and Deep Learning models have shown a surprising capacity for solving complex tasks in recent years.
no code implementations • 25 Sep 2019 • Luis A. Perez Rey, Dmitri Jarnikov, Mike Holenderski
The amount of labelled data for pose estimation is relatively limited.