Searched for: subject%3A%22equivariance%22
(1 - 17 of 17)
document
Lengyel, A. (author)
Computer vision algorithms are getting more advanced by the day and slowly approach human-like capabilities, such as detecting objects in cluttered scenes and recognizing facial expressions. Yet, computers learn to perform these tasks very differently from humans. Where humans can generalize between different lighting conditions or geometric...
doctoral thesis 2024
document
Basting, Mark (author)
In real-life scenarios, there are many variations in sizes of objects of the same category and the objects are not always placed at a fixed distance from the camera. This results in objects taking up an arbitrary size of pixels in the image. Vanilla CNNs are by design only translation equivariant and thus have to learn separate filters for...
master thesis 2023
document
Lieuw A Soe, Devin (author)
This paper studies the effect of integrating color equivariance and invariance into object detection, in particular into the Faster R-CNN architecture. To better understand the influence of this integration, we introduce modifications to the traditional convolutional layers of the standard Faster R-CNN model. By employing group theory in a...
master thesis 2023
document
Edixhoven, Tom (author)
In this work we show how Group Equivariant Convolutional Neural Networks use subsampling to learn to break equivariance to their symmetries. We focus on the 2D roto-translation group and investigate the impact of broken equivariance on network performance. We show that changing the input dimension of a network by as little as a single pixel can...
master thesis 2023
document
Lengyel, A. (author), Strafforello, O. (author), Bruintjes, R. (author), Gielisse, A.S. (author), van Gemert, J.C. (author)
Color is a crucial visual cue readily exploited by Convolutional Neural Networks (CNNs) for object recognition. However, CNNs struggle if there is data imbalance between color variations introduced by accidental recording conditions. Color invariance addresses this issue but does so at the cost of removing all color information, which sacrifices...
conference paper 2023
document
Motyka, Tomasz (author)
Aside from developing methods to embed the equivariant priors into the architectures, one can also study how the networks learn equivariant properties. In this work, we conduct a study on the influence of different factors on learned equivariance. We propose a method to quantify equivariance and argue why using the correlation to compare...
master thesis 2022
document
Odolinski, Robert (author), Teunissen, P.J.G. (author)
The best integer equivariant (BIE) estimator for the multivariate t-distribution was introduced in Teunissen (J Geod, 2020. https://doi.org/10.1007/s00190-020-01407-2), where it was shown that the BIE-weights will be different from that of the normal distribution. In this contribution, we analyze these BIE estimators while making use of multi...
journal article 2022
document
Basu, Debadeep (author)
This work applies the theory of group equivariance to the domain of video action recognition replacing standard 3Dconvolutions with group convolutions which are equivariant to temporal direction, and multiples of 90-degree spatial rotations. We propose a temporal direction symmetry group T2 and extend the standard planar rotations group to three...
master thesis 2021
document
Hoogenberg, Ruben (author)
In this thesis we have looked into the complexity of neural networks. Especially convolutional neural networks (CNNs), which are useful for image recognition, are looked into. In order to better understand the process in the neural networks, in the first half of this report a mathematical foundation for neural networks and CNNs is constructed....
bachelor thesis 2021
document
Diez, T. (author), Rudolph, Gerd (author)
Local normal form theorems for smooth equivariant maps between infinite-dimensional manifolds are established. These normal form results are new even in finite dimensions. The proof is inspired by the Lyapunov–Schmidt reduction for dynamical systems and by the Kuranishi method for moduli spaces. It uses a slice theorem for Fréchet manifolds...
journal article 2021
document
Iancu, Bianca (author)
Network data are essential in applications such as recommender systems, social networks, and sensor networks. A unique characteristic that these data encompass is the coupling between the data values and the underlying network structure on which these data are defined. Graph Neural Networks (GNNs) have been designed as tools to extend the...
master thesis 2020
document
Wiersma, R.T. (author), Eisemann, E. (author), Hildebrandt, K.A. (author)
This paper is concerned with a fundamental problem in geometric deep learning that arises in the construction of convolutional neural networks on surfaces. Due to curvature, the transport of filter kernels on surfaces results in a rotational ambiguity, which prevents a uniform alignment of these kernels on the surface. We propose a network...
journal article 2020
document
van der Pol, Elise (author), Kipf, Thomas (author), Oliehoek, F.A. (author), Welling, Max (author)
This work exploits action equivariance for representation learning in reinforcement learning. Equivariance under actions states that transitions in the input space are mirrored by equivalent transitions in latent space, while the map and transition functions should also commute. We introduce a contrastive loss function that enforces action...
conference paper 2020
document
Teunissen, P.J.G. (author)
This contribution extends the theory of integer equivariant estimation (Teunissen in J Geodesy 77:402–410, 2003) by developing the principle of best integer equivariant (BIE) estimation for the class of elliptically contoured distributions. The presented theory provides new minimum mean squared error solutions to the problem of GNSS carrier...
journal article 2020
document
Odolinski, Robert (author), Teunissen, P.J.G. (author)
The key to precise global navigation satellite system (GNSS) positioning is carrier phase integer ambiguity resolution with a high success rate. On the other hand when the success rate is too low, the user will normally prefer the float solution. The alternative can be to use the best integer equivariant (BIE) estimator, since it is optimal in...
journal article 2020
document
Wiersma, Ruben (author)
We present a new approach for deep learning on surfaces, combining geometric convolutional networks with rotationally equivariant networks. Existing work either learns rotationally invariant filters, or learns filters in the tangent plane without correctly relating orientations between different tangent planes (orientation ambiguity). We propose...
master thesis 2019
document
Teunissen, P.J.G. (author)
journal article 2007
Searched for: subject%3A%22equivariance%22
(1 - 17 of 17)