Learnable Gabor modulated complex-valued networks for orientation
robustness
- URL: http://arxiv.org/abs/2011.11734v2
- Date: Tue, 5 Oct 2021 18:01:10 GMT
- Title: Learnable Gabor modulated complex-valued networks for orientation
robustness
- Authors: Felix Richards, Adeline Paiement, Xianghua Xie, Elisabeth Sola,
Pierre-Alain Duc
- Abstract summary: Learnable Gabor Convolutional Networks (LGCNs) are parameter-efficient and offer increased model complexity.
We investigate the robustness of complex valued convolutional weights with learned Gabor filters to enable orientation transformations.
- Score: 4.024850952459758
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Robustness to transformation is desirable in many computer vision tasks,
given that input data often exhibits pose variance. While translation
invariance and equivariance is a documented phenomenon of CNNs, sensitivity to
other transformations is typically encouraged through data augmentation. We
investigate the modulation of complex valued convolutional weights with learned
Gabor filters to enable orientation robustness. The resulting network can
generate orientation dependent features free of interpolation with a single set
of learnable rotation-governing parameters. By choosing to either retain or
pool orientation channels, the choice of equivariance versus invariance can be
directly controlled. Moreover, we introduce rotational weight-tying through a
proposed cyclic Gabor convolution, further enabling generalisation over
rotations. We combine these innovations into Learnable Gabor Convolutional
Networks (LGCNs), that are parameter-efficient and offer increased model
complexity. We demonstrate their rotation invariance and equivariance on MNIST,
BSD and a dataset of simulated and real astronomical images of Galactic cirri.
Related papers
- Revisiting Data Augmentation for Rotational Invariance in Convolutional
Neural Networks [0.29127054707887967]
We investigate how best to include rotational invariance in a CNN for image classification.
Our experiments show that networks trained with data augmentation alone can classify rotated images nearly as well as in the normal unrotated case.
arXiv Detail & Related papers (2023-10-12T15:53:24Z) - FRS-Nets: Fourier Parameterized Rotation and Scale Equivariant Networks
for Retinal Vessel Segmentation [55.4653338610275]
We construct a novel convolution operator (FRS-Conv), which is Fourier parameterized and equivariant to rotation and scaling.
With merely 13.9% parameters of corresponding baselines, FRS-Nets have achieved state-of-the-art performance.
It demonstrates the remarkable accuracy, generalization, and clinical application potential of FRS-Nets.
arXiv Detail & Related papers (2023-09-27T13:14:57Z) - Deep Neural Networks with Efficient Guaranteed Invariances [77.99182201815763]
We address the problem of improving the performance and in particular the sample complexity of deep neural networks.
Group-equivariant convolutions are a popular approach to obtain equivariant representations.
We propose a multi-stream architecture, where each stream is invariant to a different transformation.
arXiv Detail & Related papers (2023-03-02T20:44:45Z) - Orthonormal Convolutions for the Rotation Based Iterative
Gaussianization [64.44661342486434]
This paper elaborates an extension of rotation-based iterative Gaussianization, RBIG, which makes image Gaussianization possible.
In images its application has been restricted to small image patches or isolated pixels, because rotation in RBIG is based on principal or independent component analysis.
We present the emphConvolutional RBIG: an extension that alleviates this issue by imposing that the rotation in RBIG is a convolution.
arXiv Detail & Related papers (2022-06-08T12:56:34Z) - B-cos Networks: Alignment is All We Need for Interpretability [136.27303006772294]
We present a new direction for increasing the interpretability of deep neural networks (DNNs) by promoting weight-input alignment during training.
A B-cos transform induces a single linear transform that faithfully summarises the full model computations.
We show that it can easily be integrated into common models such as VGGs, ResNets, InceptionNets, and DenseNets.
arXiv Detail & Related papers (2022-05-20T16:03:29Z) - Improving the Sample-Complexity of Deep Classification Networks with
Invariant Integration [77.99182201815763]
Leveraging prior knowledge on intraclass variance due to transformations is a powerful method to improve the sample complexity of deep neural networks.
We propose a novel monomial selection algorithm based on pruning methods to allow an application to more complex problems.
We demonstrate the improved sample complexity on the Rotated-MNIST, SVHN and CIFAR-10 datasets.
arXiv Detail & Related papers (2022-02-08T16:16:11Z) - Training or Architecture? How to Incorporate Invariance in Neural
Networks [14.162739081163444]
We propose a method for provably invariant network architectures with respect to group actions.
In a nutshell, we intend to 'undo' any possible transformation before feeding the data into the actual network.
We analyze properties of such approaches, extend them to equivariant networks, and demonstrate their advantages in terms of robustness as well as computational efficiency in several numerical examples.
arXiv Detail & Related papers (2021-06-18T10:31:00Z) - Rotated Ring, Radial and Depth Wise Separable Radial Convolutions [13.481518628796692]
In this work, we address trainable rotation invariant convolutions and the construction of nets.
On the one hand, we show that our approach is rotationally invariant for different models and on different public data sets.
The rotationally adaptive convolution models presented are more computationally intensive than normal convolution models.
arXiv Detail & Related papers (2020-10-02T09:01:51Z) - Generalizing Convolutional Neural Networks for Equivariance to Lie
Groups on Arbitrary Continuous Data [52.78581260260455]
We propose a general method to construct a convolutional layer that is equivariant to transformations from any specified Lie group.
We apply the same model architecture to images, ball-and-stick molecular data, and Hamiltonian dynamical systems.
arXiv Detail & Related papers (2020-02-25T17:40:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.