Relaxed Rotational Equivariance via $G$-Biases in Vision
- URL: http://arxiv.org/abs/2408.12454v3
- Date: Tue, 14 Jan 2025 15:35:55 GMT
- Title: Relaxed Rotational Equivariance via $G$-Biases in Vision
- Authors: Zhiqiang Wu, Yingjie Liu, Licheng Sun, Jian Yang, Hanlin Dong, Shing-Ho J. Lin, Xuan Tang, Jinpeng Mi, Bo Jin, Xian Wei,
- Abstract summary: Group Equivariant Convolution (GConv) can capture rotational equivariance from original data.
However, the presentation or distribution of real-world data rarely conforms to strict rotational equivariance.
We propose a simple but highly effective method to address this problem, which utilizes a set of learnable biases called $G$-Biases.
Experiments demonstrate that the proposed RREConv-based methods achieve excellent performance compared to existing GConv-based methods in both classification and 2D object detection tasks.
- Score: 19.814324876189772
- License:
- Abstract: Group Equivariant Convolution (GConv) can capture rotational equivariance from original data. It assumes uniform and strict rotational equivariance across all features as the transformations under the specific group. However, the presentation or distribution of real-world data rarely conforms to strict rotational equivariance, commonly referred to as Rotational Symmetry-Breaking (RSB) in the system or dataset, making GConv unable to adapt effectively to this phenomenon. Motivated by this, we propose a simple but highly effective method to address this problem, which utilizes a set of learnable biases called $G$-Biases under the group order to break strict group constraints and then achieve a Relaxed Rotational Equivariant Convolution (RREConv). To validate the efficiency of RREConv, we conduct extensive ablation experiments on the discrete rotational group $\mathcal{C}_n$. Experiments demonstrate that the proposed RREConv-based methods achieve excellent performance compared to existing GConv-based methods in both classification and 2D object detection tasks on the natural image datasets.
Related papers
- Harmformer: Harmonic Networks Meet Transformers for Continuous Roto-Translation Equivariance [2.5864824580604515]
CNNs exhibit inherent equivariance to image translation, leading to efficient parameter and data usage, faster learning, and improved robustness.
The concept of translation equivariant networks has been successfully extended to rotation transformation using group convolution for discrete rotation groups and harmonic functions for the continuous rotation group encompassing $360circ$.
We introduce the Harmformer, a harmonic transformer with a convolutional stem that achieves equivariance for both translation and continuous rotation.
arXiv Detail & Related papers (2024-11-06T09:39:25Z) - SBDet: A Symmetry-Breaking Object Detector via Relaxed Rotation-Equivariance [26.05910177212846]
Group Equivariant Convolution (GConv) empowers models to explore symmetries hidden in visual data, improving their performance.
Traditional GConv methods are limited by the strict operation rules in the group space, making it difficult to adapt to Symmetry-Breaking or non-rigid transformations.
We propose a novel Relaxed Rotation-Equivariant Network (R2Net) as the backbone and further develop the Symmetry-Breaking Object Detector (SBDet) for 2D object detection built upon it.
arXiv Detail & Related papers (2024-08-21T16:32:03Z) - Equivariant Disentangled Transformation for Domain Generalization under
Combination Shift [91.38796390449504]
Combinations of domains and labels are not observed during training but appear in the test environment.
We provide a unique formulation of the combination shift problem based on the concepts of homomorphism, equivariance, and a refined definition of disentanglement.
arXiv Detail & Related papers (2022-08-03T12:31:31Z) - 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) - 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) - Deformation Robust Roto-Scale-Translation Equivariant CNNs [10.44236628142169]
Group-equivariant convolutional neural networks (G-CNNs) achieve significantly improved generalization performance with intrinsic symmetry.
General theory and practical implementation of G-CNNs have been studied for planar images under either rotation or scaling transformation.
arXiv Detail & Related papers (2021-11-22T03:58:24Z) - Examining and Combating Spurious Features under Distribution Shift [94.31956965507085]
We define and analyze robust and spurious representations using the information-theoretic concept of minimal sufficient statistics.
We prove that even when there is only bias of the input distribution, models can still pick up spurious features from their training data.
Inspired by our analysis, we demonstrate that group DRO can fail when groups do not directly account for various spurious correlations.
arXiv Detail & Related papers (2021-06-14T05:39:09Z) - Exploiting Learned Symmetries in Group Equivariant Convolutions [20.63056707649319]
Group Equivariant Convolutions (GConvs) enable convolutional neural networks to be equivariant to various transformation groups.
We show that GConvs can be efficiently decomposed into depthwise separable convolutions.
arXiv Detail & Related papers (2021-06-09T08:50:22Z) - GroupifyVAE: from Group-based Definition to VAE-based Unsupervised
Representation Disentanglement [91.9003001845855]
VAE-based unsupervised disentanglement can not be achieved without introducing other inductive bias.
We address VAE-based unsupervised disentanglement by leveraging the constraints derived from the Group Theory based definition as the non-probabilistic inductive bias.
We train 1800 models covering the most prominent VAE-based models on five datasets to verify the effectiveness of our method.
arXiv Detail & Related papers (2021-02-20T09:49:51Z) - Group Equivariant Conditional Neural Processes [30.134634059773703]
We present the group equivariant conditional neural process (EquivCNP)
We show that EquivCNP achieves comparable performance to conventional conditional neural processes in a 1D regression task.
arXiv Detail & Related papers (2021-02-17T13:50:07Z) - 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.