Hugging Face Trending Papers June 24, 2026

REViT: Roto-reflection Equivariant Convolutional Vision Transformer

Read the original on Hugging Face Trending Papers →

In this paper, we propose a discrete roto-reflection group equivariant vision transformer with convolutional attention. Roto-reflection equivariant networks preserve the rotational, flip and positional symmetry in feature maps, making them useful for tasks where orientation of the inputs is relevant to the model outputs.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning

Jun 25

REViT: Roto-reflection Equivariant Convolutional Vision Transformer

arXiv:2606. 25318v1 Announce Type: cross Abstract: In this paper, we propose a discrete roto-reflection group equivariant vision transformer with convolutional attention.

By Sheir A. Zaheer, Alexander C. Holston, Chan Y. Park

llms computer-vision

arXiv Machine Learning

Jun 29

A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\mathrm{O}(2)$

arXiv:2606. 27864v1 Announce Type: cross Abstract: Vision transformers have become a dominant architecture for visual recognition.

By T\={\i}kun \^Ong, Georg B\"okman

llms

arXiv Machine Learning

Aug 3

Moment kernels: a simple and scalable approach for equivariance to rotations and reflections in deep convolutional networks

arXiv:2505. 21736v2 Announce Type: replace-cross Abstract: Translation equivariance is a central reason convolutional neural networks have been successful in computer vision.

By Siqi Fang, Zachary Schlamowitz, Andrew Bennecke, Daniel J. Tward

computer-vision

arXiv Machine Learning

Jul 7

On Preserving Geometrical Invariance for Superpixel Image Classification using Graph Transformer

arXiv:2607. 04262v1 Announce Type: new Abstract: Convolutional Neural Network (CNN) and Vision Transformer (ViT) for image classification exploit a dense grid of pixels containing redundant information.

By Sarabeshwar Balaji, Shubham Mohanty, Akash Anil

llms computer-vision benchmarks

Hugging Face Trending Papers

Aug 11

Grid-Preserving Knowledge Distillation: Transferring Convolutional Inductive Bias to Vision Transformers under Data Scarcity

Vision Transformers underperform convolutional networks when training data is scarce, and distilling convolutional inductive biases from a CNN teacher is an effective remedy that leaves the deployed model unchanged. General-purpose feature distillation, however, transfers little in this setting.

llms efficiency benchmarks safety

arXiv AI

1d ago

Geometrically Constrained and Token-Based Probabilistic Spatial Transformers

arXiv:2509. 11218v2 Announce Type: replace-cross Abstract: Spatial transformations such as rotation and scale obscure the morphological cues needed for accurate image classification.

By Johann Schmidt, Sebastian Stober

llms computer-vision benchmarks

Related stories

REViT: Roto-reflection Equivariant Convolutional Vision Transformer

A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\mathrm{O}(2)$

Moment kernels: a simple and scalable approach for equivariance to rotations and reflections in deep convolutional networks

On Preserving Geometrical Invariance for Superpixel Image Classification using Graph Transformer

Grid-Preserving Knowledge Distillation: Transferring Convolutional Inductive Bias to Vision Transformers under Data Scarcity

Geometrically Constrained and Token-Based Probabilistic Spatial Transformers