English
Related papers

Related papers: Equivariant Transformer Networks

200 papers

Learning self-supervised representations that are invariant and equivariant to transformations is crucial for advancing beyond traditional visual classification tasks. However, many methods rely on predictor architectures to encode…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Athinoulla Konstantinou , Georgios Leontidis , Mamatha Thota , Aiden Durrant

Vision Transformers (ViTs) have revolutionized computer vision by leveraging self-attention to model long-range dependencies. However, ViTs face challenges such as high computational costs due to the quadratic scaling of self-attention and…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Zhoujie Qian

In this paper, we introduce group convolutional neural networks (GCNNs) equivariant to color variation. GCNNs have been designed for a variety of geometric transformations from 2D and 3D rotation groups, to semi-groups such as scale.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Yulong Yang , Felix O'Mahony , Christine Allen-Blanchette

Current generative models, such as autoregressive and diffusion approaches, decompose high-dimensional data distribution learning into a series of simpler subtasks. However, inherent conflicts arise during the joint optimization of these…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Ruixiao Dong , Mengde Xu , Zigang Geng , Li Li , Han Hu , Shuyang Gu

We introduce the Graded Transformer framework, a new class of sequence models that embeds algebraic inductive biases through grading transformations on vector spaces. Extending Graded Neural Networks (GNNs), we propose two architectures:…

Machine Learning · Computer Science 2025-09-03 Tony Shaska

Equivariant neural networks offer strong inductive biases for learning from molecular and geometric data but often rely on specialized, computationally expensive tensor operations. We present a framework to transfers existing tensor field…

Machine Learning · Computer Science 2025-10-01 Gerrit Gerhartz , Peter Lippmann , Fred A. Hamprecht

Despite their widespread success in various domains, Transformer networks have yet to perform well across datasets in the domain of 3D atomistic graphs such as molecules even when 3D-related inductive biases like translational invariance…

Machine Learning · Computer Science 2023-03-01 Yi-Lun Liao , Tess Smidt

The Euler Characteristic Transform (ECT) is an efficiently-computable geometrical-topological invariant that characterizes the global shape of data. In this paper, we introduce the Local Euler Characteristic Transform ($\ell$-ECT), a novel…

Machine Learning · Computer Science 2025-05-29 Julius von Rohrscheidt , Bastian Rieck

Spherical convolutional networks have been introduced recently as tools to learn powerful feature representations of 3D shapes. Spherical CNNs are equivariant to 3D rotations making them ideally suited to applications where 3D data may be…

Computer Vision and Pattern Recognition · Computer Science 2019-05-16 Carlos Esteves , Avneesh Sud , Zhengyi Luo , Kostas Daniilidis , Ameesh Makadia

Visual Transformers (VTs) are emerging as an architectural paradigm alternative to Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations between image elements and they potentially have a larger…

Computer Vision and Pattern Recognition · Computer Science 2021-11-16 Yahui Liu , Enver Sangineto , Wei Bi , Nicu Sebe , Bruno Lepri , Marco De Nadai

The Symmetric group $S_{n}$ manifests itself in large classes of quantum systems as the invariance of certain characteristics of a quantum state with respect to permuting the qubits. The subgroups of $S_{n}$ arise, among many other…

Quantum Physics · Physics 2024-11-19 Sreetama Das , Filippo Caruso

We introduce an $E(n)$-equivariant Transformer architecture for spatio-temporal graph data. By imposing rotation, translation, and permutation equivariance inductive biases in both space and time, we show that the Spacetime…

Machine Learning · Computer Science 2024-08-13 Sergio G. Charles

Equivariant and invariant deep learning models have been developed to exploit intrinsic symmetries in data, demonstrating significant effectiveness in certain scenarios. However, these methods often suffer from limited representation…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Yulu Bai , Jiahong Fu , Qi Xie , Deyu Meng

Equivariance guarantees that a model's predictions capture key symmetries in data. When an image is translated or rotated, an equivariant model's representation of that image will translate or rotate accordingly. The success of…

Machine Learning · Computer Science 2024-06-19 Nate Gruver , Marc Finzi , Micah Goldblum , Andrew Gordon Wilson

In reinforcement learning (RL), exploiting environmental symmetries can significantly enhance efficiency, robustness, and performance. However, ensuring that the deep RL policy and value networks are respectively equivariant and invariant…

Machine Learning · Computer Science 2024-12-31 Mirco Theile , Hongpeng Cao , Marco Caccamo , Alberto L. Sangiovanni-Vincentelli

In many unpaired image domain translation problems, e.g., style transfer or super-resolution, it is important to keep the translated image similar to its respective input image. We propose the extremal transport (ET) which is a mathematical…

Machine Learning · Computer Science 2023-11-03 Milena Gazdieva , Alexander Korotin , Daniil Selikhanovych , Evgeny Burnaev

Invariant and equivariant networks have been successfully used for learning images, sets, point clouds, and graphs. A basic challenge in developing such networks is finding the maximal collection of invariant and equivariant linear layers.…

Machine Learning · Computer Science 2019-05-01 Haggai Maron , Heli Ben-Hamu , Nadav Shamir , Yaron Lipman

The simplicity and effectiveness of the UNet architecture makes it ubiquitous in image restoration, image segmentation, and diffusion models. They are often assumed to be equivariant to translations, yet they traditionally consist of layers…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Jérémy Scanvic , Quentin Barthélemy , Julián Tachella

In recent years, the use of machine learning has become increasingly popular in the context of lattice field theories. An essential element of such theories is represented by symmetries, whose inclusion in the neural network properties can…

High Energy Physics - Lattice · Physics 2021-12-24 Srinath Bulusu , Matteo Favoni , Andreas Ipp , David I. Müller , Daniel Schuh

Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input image translations produce proportionate feature map…

Computer Vision and Pattern Recognition · Computer Science 2017-04-12 Daniel E. Worrall , Stephan J. Garbin , Daniyar Turmukhambetov , Gabriel J. Brostow